- Published on
• State Key Lab of CAD&CG, Zhejiang University• vivo Mobile Communication Co. Ltd
Spatial-relationships
Show all tags
- large-language-models (731)
- machine-learning (219)
- deep-learning (192)
- diffusion-models (149)
- reinforcement-learning (108)
- vision-language-models (97)
- computational-efficiency (94)
- neural-networks (89)
- natural-language-processing (88)
- computer-vision (84)
- artificial-intelligence (83)
- benchmark-datasets (79)
- generalization (75)
- generative-models (75)
- deep-neural-networks (73)
- robustness (73)
- benchmarking (70)
- fine-tuning (69)
- graph-neural-networks (66)
- evaluation-metrics (63)
- datasets (62)
- multimodal-large-language-models (60)
- federated-learning (58)
- image-generation (58)
- computational-costs (57)
- autonomous-driving (57)
- scalability (56)
- adversarial-attacks (56)
- self-supervised-learning (55)
- model-performance (54)
- convolutional-neural-networks (52)
- interpretability (50)
- object-detection (50)
- data-augmentation (49)
- accuracy (49)
- feature-extraction (49)
- performance-evaluation (47)
- classification (46)
- retrieval-augmented-generation (46)
- benchmark (45)
- state-of-the-art-performance (44)
- language-models (44)
- robotics (43)
- semantic-segmentation (43)
- attention-mechanism (42)
- efficiency (41)
- 3d-gaussian-splatting (41)
- generative-ai (39)
- foundation-models (38)
- few-shot-learning (38)
- contrastive-learning (38)
- vision-transformers (38)
- in-context-learning (37)
- transformers (35)
- data-privacy (35)
- knowledge-graphs (34)
- image-classification (34)
- text-to-image-generation (33)
- synthetic-datasets (33)
- transfer-learning (32)
- real-world-datasets (32)
- novel-view-synthesis (32)
- synthetic-data (31)
- knowledge-distillation (31)
- video-generation (31)
- low-resource-languages (30)
- deep-learning-models (29)
- machine-learning-models (29)
- performance-improvement (29)
- generalizability (29)
- 3d-reconstruction (29)
- transformer-based-models (28)
- large-vision-language-models (28)
- zero-shot-learning (28)
- catastrophic-forgetting (28)
- classification-accuracy (25)
- anomaly-detection (25)
- decision-making (25)
- differential-privacy (25)
- multi-task-learning (25)
- optimization (25)
- f1-score (24)
- computational-complexity (24)
- transparency (24)
- clip (24)
- domain-adaptation (24)
- model-evaluation (24)
- loss-function (23)
- generative-adversarial-networks (23)
- model-architectures (23)
- unsupervised-learning (23)
- autonomous-vehicles (22)
- benchmark-evaluation (22)
- transformer-architecture (22)
- llms (22)
- multimodal-models (22)
- question-answering (22)
- healthcare (21)
- representation-learning (21)
- downstream-tasks (21)
- text-generation (21)
- remote-sensing (21)
- gaussian-splatting (21)
- energy-efficiency (21)
- model-robustness (21)
- simulation (20)
- computational-resources (20)
- experimental-results (20)
- parameter-efficient-fine-tuning (20)
- segmentation (20)
- image-processing (20)
- video-diffusion-models (20)
- human-evaluation (20)
- inference-speed (20)
- visual-question-answering (20)
- sample-efficiency (20)
- point-clouds (19)
- classification-tasks (19)
- explainability (19)
- supervised-learning (19)
- evaluation (19)
- temporal-consistency (19)
- computational-overhead (19)
- image-quality (19)
- self-attention (19)
- multi-agent-systems (19)
- hallucinations (19)
- sentiment-analysis (19)
- partial-differential-equations (18)
- reliability (18)
- active-learning (18)
- privacy (18)
- low-rank-adaptation (18)
- latent-space (18)
- uncertainty-quantification (18)
- recommendation-systems (18)
- privacy-concerns (18)
- medical-imaging (18)
- clustering (18)
- numerical-experiments (17)
- domain-shift (17)
- real-world-applications (17)
- prompt-engineering (17)
- bayesian-optimization (17)
- image-restoration (17)
- continual-learning (17)
- adversarial-training (17)
- synthetic-data-generation (17)
- dataset-creation (17)
- stable-diffusion (17)
- deep-reinforcement-learning (17)
- human-computer-interaction (17)
- knowledge-transfer (17)
- class-imbalance (17)
- gpt-4 (17)
- training-efficiency (17)
- training-data (16)
- explainable-ai (16)
- unmanned-aerial-vehicles (16)
- variational-autoencoder (16)
- spiking-neural-networks (16)
- visual-quality (16)
- large-multimodal-models (16)
- transformer-models (16)
- image-reconstruction (16)
- neural-radiance-fields (16)
- latent-diffusion-models (16)
- evaluation-benchmarks (16)
- supervised-fine-tuning (16)
- state-of-the-art-methods (16)
- code-generation (16)
- evaluation-methods (16)
- image-segmentation (16)
- instruction-tuning (16)
- dynamic-environments (15)
- dynamical-systems (15)
- overfitting (15)
- adversarial-robustness (15)
- machine-translation (15)
- data-scarcity (15)
- diffusion-transformers (15)
- inverse-problems (15)
- named-entity-recognition (15)
- information-retrieval (15)
- feature-representations (15)
- transferability (15)
- semantic-information (15)
- direct-preference-optimization (15)
- decision-tree (14)
- mixture-of-experts (14)
- empirical-evaluations (14)
- misinformation (14)
- generalization-capabilities (14)
- image-synthesis (14)
- text-to-image-models (14)
- dimensionality-reduction (14)
- reasoning (14)
- high-resolution-images (14)
- social-media (14)
- mathematical-reasoning (14)
- zero-shot-generalization (14)
- nuscenes-dataset (14)
- denoising (14)
- meta-learning (13)
- sample-complexity (13)
- uncertainty-estimation (13)
- pre-trained-models (13)
- hyperparameter-tuning (13)
- recurrent-neural-networks (13)
- virtual-reality (13)
- text-to-image-diffusion-models (13)
- multi-agent-reinforcement-learning (13)
- cnns (13)
- depth-estimation (13)
- generalization-ability (13)
- image-captioning (13)
- evaluation-framework (13)
- natural-language-understanding (13)
- self-attention-mechanism (13)
- semi-supervised-learning (13)
- latent-representations (13)
- large-scale-datasets (13)
- autonomous-agents (13)
- video-understanding (13)
- data-processing (13)
- user-experience (13)
- optimization-problem (13)
- fairness (13)
- contextual-information (13)
spatial-relationships (12)
- imitation-learning (12)
- data-efficiency (12)
- time-series-forecasting (12)
- human-robot-interaction (12)
- model-accuracy (12)
- sustainability (12)
- personalization (12)
- model-training (12)
- localization (12)
- segment-anything-model (12)
- augmented-reality (12)
- image-editing (12)
- real-world-scenarios (12)
- explainable-artificial-intelligence (12)
- autoregressive-models (12)
- data-quality (12)
- quantum-machine-learning (12)
- jailbreak-attacks (12)
- distribution-shifts (12)
- satellite-imagery (11)
- physics-informed-neural-networks (11)
- predictive-accuracy (11)
- diffusion-based-model (11)
- convergence (11)
- ensemble-learning (11)
- prediction-accuracy (11)
- neural-network-architectures (11)
- monte-carlo-tree-search (11)
- autoencoders (11)
- gpt-4o (11)
- inpainting (11)
- text-to-video-generation (11)
- occlusions (11)
- performance-metrics (11)
- classifier-free-guidance (11)
- temporal-dynamics (11)
- attack-success-rates (11)
- detection-accuracy (11)
- rgb-images (11)
- generative-tasks (11)
- memory-efficiency (11)
- random-forest (11)
- causal-inference (11)
- reconstruction-quality (11)
- gradient-descent (11)
- medical-image-segmentation (11)
- generative-modeling (11)
- human-feedback (11)
- computational-demands (11)
- support-vector-machine (10)
- performance-enhancement (10)
- data-heterogeneity (10)
- safety (10)
- link-prediction (10)
- predictive-performance (10)
- machine-unlearning (10)
- adaptability (10)
- data-generation (10)
- multi-modal-large-language-models (10)
- cross-attention (10)
- motion-planning (10)
- 3d-scene-reconstruction (10)
- visual-grounding (10)
- event-cameras (10)
- monocular-videos (10)
- dynamic-scenes (10)
- edge-computing (10)
- energy-consumption (10)
- 3d-representations (10)
- automatic-speech-recognition (10)
- chain-of-thought-reasoning (10)
- defense-mechanisms (10)
- super-resolution (10)
- structural-information (10)
- backdoor-attacks (10)
- bert (10)
- mobile-devices (10)
- embodied-ai (10)
- pretraining (10)
- instance-segmentation (10)
- 3d-object-detection (10)
- classification-performance (10)
- kolmogorov-arnold-networks (10)
- machine-learning-algorithms (10)
- security (10)
- signal-to-noise-ratio (10)
- diagnostic-accuracy (10)
- quantization (10)
- time-series-data (10)
- sparsity (10)
- quantitative-metrics (10)
- visual-language-models (10)
- bias (10)
- domain-generalization (10)
- model-compression (10)
- language-modeling (9)
- feature-selection (9)
- long-short-term-memory (9)
- resource-allocation (9)
- error-analysis (9)
- real-time-performance (9)
- deep-generative-models (9)
- convergence-rate (9)
- stability (9)
- uncertainty (9)
- complex-reasoning-tasks (9)
- planning (9)
- hyperparameters (9)
- software-engineering (9)
- stochastic-gradient-descent (9)
- label-noise (9)
- 3d-point-clouds (9)
- evaluation-datasets (9)
- robotic-manipulation (9)
- domain-specific-knowledge (9)
- inference-efficiency (9)
- face-recognition (9)
- yolov8 (9)
- ensemble-methods (9)
- text-classification (9)
- temporal-information (9)
- transformer-based-architecture (9)
- training-free-methods (9)
- accuracy-improvement (9)
- multi-view-images (9)
- predictive-modeling (9)
- predictive-models (9)
- trustworthiness (9)
- precision (9)
- curriculum-learning (9)
- multi-objective-optimization (9)
- autonomous-systems (9)
- real-time-applications (9)
- statistical-analysis (9)
- multimodal-datasets (9)
- zero-shot-classification (9)
- sparse-autoencoders (9)
- small-language-models (9)
- latency (9)
- quantitative-evaluation (9)
- hyperparameter-optimization (9)
- temporal-coherence (9)
- out-of-distribution-detection (9)
- pseudo-labels (9)
- medical-images (9)
- reproducibility (9)
- theoretical-analysis (9)
- high-dimensional-data (9)
- reasoning-capabilities (9)
- alignment (9)
- real-time-rendering (9)
- policy-optimization (9)
- next-token-prediction (9)
- state-space-models (9)
- regularization-techniques (8)
- real-world-data (8)
- programming-languages (8)
- operational-efficiency (8)
- multimodal-tasks (8)
- graph-representation-learning (8)
- generative-artificial-intelligence (8)
- node-classification (8)
- robot-navigation (8)
- sequential-decision-making (8)
- feature-space (8)
- performance-degradation (8)
- vulnerabilities (8)
- gaussian-mixture-model (8)
- scene-understanding (8)
- implicit-neural-representations (8)
- data-collection (8)
- cifar-10 (8)
- parameter-estimation (8)
- medical-image-analysis (8)
- visual-features (8)
- brain-computer-interface (8)
- unsupervised-domain-adaptation (8)
- cross-modal-alignment (8)
- reinforcement-learning-from-human-feedback (8)
- reward-model (8)
- optical-flow (8)
- depth-maps (8)
- denoising-process (8)
- camera-poses (8)
- domain-gaps (8)
- ai-agents (8)
- policy-learning (8)
- generalization-performance (8)
- deepfake-detection (8)
- text-embeddings (8)
- xgboost (8)
- pose-estimation (8)
- low-light-image-enhancement (8)
- neural-machine-translation (8)
- world-models (8)
- nlp (8)
- contrastive-loss (8)
- 3d-gaussians (8)
- cloud-computing (8)
- magnetic-resonance-imaging (8)
- user-preferences (8)
- binary-classification (8)
- resource-constrained-environments (8)
- optical-character-recognition (8)
- taxonomy (8)
- mutual-information (8)
- experiments (8)
- operator-learning (8)
- cybersecurity (8)
- electronic-health-records (8)
- pre-trained-language-models (8)
- image-super-resolution (8)
- tokenization (8)
- experimental-validation (8)
- rendering-quality (8)
- multi-layer-perceptrons (8)
- edge-devices (8)
- chain-of-thought (8)
- trajectory-prediction (8)
- positional-encoding (8)
- information-loss (8)
- dataset-construction (8)
- tabular-data (8)
- embeddings (8)
- inference-time (8)
- mobile-robots (8)
- black-box-models (8)
- real-world-experiments (7)
- memorization (7)
- trajectory-planning (7)
- trust (7)
- digital-twin (7)
- combinatorial-optimization (7)
- gaussian-noise (7)
- temporal-dependencies (7)
- probability-distributions (7)
- model-interpretability (7)
- humanoid-robots (7)
- data-leakage (7)
- visual-perception (7)
- hybrid-models (7)
- training-datasets (7)
- safety-alignment (7)
- natural-language-instructions (7)
- flow-matching (7)
- neural-rendering (7)
- finetuning (7)
- stochasticity (7)
- video-analysis (7)
- multilingual-models (7)
- public-datasets (7)
- object-tracking (7)
- spatial-transcriptomics (7)
- graph-convolutional-networks (7)
- pre-training (7)
- deep-learning-techniques (7)
- scaling-laws (7)
- inference-acceleration (7)
- cross-attention-mechanism (7)
- model-predictive-control (7)
- vision-foundation-models (7)
- performance-benchmarks (7)
- chatgpt (7)
- performance-gains (7)
- multiple-choice-questions (7)
- temporal-reasoning (7)
- semantic-relationships (7)
- proximal-policy-optimization (7)
- feature-engineering (7)
- privacy-protection (7)
- user-study (7)
- bias-mitigation (7)
- clinical-decision-making (7)
- image-analysis (7)
- fid (7)
- climate-change (7)
- semantic-understanding (7)
- embedding-space (7)
- model-size (7)
- pytorch (7)
- communication-costs (7)
- training-strategy (7)
- information-flow (7)
- text-prompts (7)
- data-diversity (7)
- pretrained-models (7)
- semantic-features (7)
- genetic-algorithms (7)
- classification-algorithms (7)
- reward-functions (7)
- inference-latency (7)
- ethical-considerations (7)
- observational-data (7)
- algorithms (7)
- semantic-alignment (7)
- memory-consumption (7)
- artificial-general-intelligence (7)
- text-to-video-models (7)
- multimodal-reasoning (7)
- image-understanding (7)
- software-development (7)
- nlp-tasks (7)
- gaussian-processes (7)
- normalizing-flows (7)
- latent-variables (7)
- training-dynamics (7)
- generative-framework (7)
- spurious-correlations (7)
- hate-speech-detection (7)
- content-moderation (7)
- logical-reasoning (7)
- benchmark-performance (7)
- adversarial-learning (7)
- manipulation-tasks (7)
- visual-fidelity (7)
- spatial-reasoning (7)
- agriculture (6)
- simulation-results (6)
- black-box-attack (6)
- hypergraphs (6)
- architecture (6)
- sensor-data (6)
- multilayer-perceptrons (6)
- evaluation-protocols (6)
- sensitivity-analysis (6)
- real-time-processing (6)
- importance-sampling (6)
- data-driven-approach (6)
- imagenet (6)
- image-quality-assessment (6)
- automation (6)
- topological-structure (6)
- gaussian-distributions (6)
- quantitative-experiments (6)
- autonomous-navigation (6)
- data-annotation (6)
- structure-from-motion (6)
- clinical-applications (6)
- context-length (6)
- adversarial-examples (6)
- quantization-techniques (6)
- robot-learning (6)
- ablation-studies (6)
- word-error-rate (6)
- dataset-diversity (6)
- human-motion-generation (6)
- user-interaction (6)
- open-source-models (6)
- proprietary-models (6)
- slam (6)
- generation-quality (6)
- dataset-evaluation (6)
- biomedical-research (6)
- data-integration (6)
- segmentation-models (6)
- inference-costs (6)
- vision-encoders (6)
- incremental-learning (6)
- comparative-analysis (6)
- autonomous-driving-systems (6)
- zero-shot-settings (6)
- coco-dataset (6)
- summarization (6)
- empirical-results (6)
- performance-comparison (6)
- resource-constrained-devices (6)
- text-to-image-synthesis (6)
- instruction-tuning-dataset (6)
- sequential-recommendation (6)
- online-learning (6)
- case-studies (6)
- regression (6)
- recall (6)
- neural-network-training (6)
- causal-graphs (6)
- research-directions (6)
- markov-decision-processes (6)
- pre-trained-diffusion-models (6)
- detection-performance (6)
- style-transfer (6)
- lidar (6)
- weakly-supervised-learning (6)
- radiology-reports (6)
- defense-strategies (6)
- generative-large-language-models (6)
- knowledge-bases (6)
- compression (6)
- regret-bounds (6)
- pruning (6)
- markov-decision-process (6)
- perturbations (6)
- scene-graphs (6)
- model-pruning (6)
- view-synthesis (6)
- task-performance (6)
- 3d-modeling (6)
- lidar-sensors (6)
- semantic-similarity (6)
- natural-language-generation (6)
- state-of-the-art-models (6)
- ai-systems (6)
- topic-modeling (6)
- neural-fields (6)
- llama-2 (6)
- image-text-alignment (6)
- k-means-clustering (6)
- accountability (6)
- recommender-systems (6)
- unlabeled-data (6)
- surrogate-models (6)
- resnet (6)
- data-synthesis (6)
- ai (6)
- visual-tokens (6)
- bayesian-inference (6)
- generalization-bounds (6)
- out-of-distribution-generalization (6)
- image-denoising (6)
- image-deblurring (6)
- interdisciplinary-collaboration (6)
- learning-based-approaches (6)
- industrial-applications (6)
- zero-shot-performance (6)
- model-fine-tuning (6)
- unet (6)
- empirical-analysis (6)
- neural-network-model (6)
- relation-extraction (6)
- model-parameters (6)
- multimodal-data (6)
- model-complexity (6)
- open-source (6)
- data-labeling (6)
- k-nearest-neighbors (5)
- u-net (5)
- supervised-contrastive-learning (5)
- autonomous-underwater-vehicles (5)
- numerical-simulations (5)
- nonlinear-systems (5)
- ablation-study (5)
- epistemic-uncertainty (5)
- fairness-in-machine-learning (5)
- personalized-federated-learning (5)
- graph-representation (5)
- safety-evaluations (5)
- localization-accuracy (5)
- mobile-applications (5)
- deep-learning-methods (5)
- transformer-blocks (5)
- affective-computing (5)
- theoretical-foundation (5)
- semantic-communication (5)
- membership-inference-attacks (5)
- multi-class-classification (5)
- data-driven-approaches (5)
- protein-language-models (5)
- shapley-values (5)
- approximation-error (5)
- privacy-preservation (5)
- trajectory-optimization (5)
- data-compression (5)
- creativity (5)
- real-time-monitoring (5)
- self-training (5)
- multi-scale-features (5)
- lora (5)
- collision-avoidance (5)
- probabilistic-models (5)
- qualitative-experiments (5)
- monocular-depth-estimation (5)
- optimal-transport (5)
- hyperspectral-imaging (5)
- early-detection (5)
- density-estimation (5)
- prompt-learning (5)
- prediction-errors (5)
- cross-attention-layers (5)
- data-sparsity (5)
- perception (5)
- data-imbalance (5)
- ai-models (5)
- multi-view-diffusion-models (5)
- empirical-validation (5)
- interoperability (5)
- low-resource-settings (5)
- camera-pose-estimation (5)
- multilingual-capabilities (5)
- cultural-contexts (5)
- biases (5)
- completeness (5)
- metrics (5)
- causal-relationships (5)
- 3d-scene-understanding (5)
- challenges (5)
- detection (5)
- training-time (5)
- 3d-scene-representation (5)
- semantic-content (5)
- visual-encoders (5)
- object-localization (5)
- inductive-bias (5)
- identity-preservation (5)
- chain-of-thought-prompting (5)
- document-retrieval (5)
- time-complexity (5)
- multi-view-stereo (5)
- embedding-models (5)
- data-representation (5)
- long-video-understanding (5)
- performance (5)
- causal-effects (5)
- optimization-algorithms (5)
- obstacle-avoidance (5)
- data-mining (5)
- noise-reduction (5)
- automatic-differentiation (5)
- estimation-error (5)
- theoretical-guarantees (5)
- risk-assessment (5)
- internet-of-things (5)
- causality (5)
- teleoperation (5)
- computed-tomography (5)
- multi-agent-collaboration (5)
- gaussian-primitives (5)
- transformer-networks (5)
- quantum-computing (5)
- transformer-encoder (5)
- multimodal-learning (5)
- whole-slide-images (5)
- compression-ratios (5)
- training-stability (5)
- resource-management (5)
- task-planning (5)
- fine-tuning-framework (5)
- simultaneous-localization-and-mapping (5)
- applications (5)
- self-improvement (5)
- legged-robots (5)
- key-value-cache (5)
- deep-learning-algorithms (5)
- sampling (5)
- information-extraction (5)
- geometric-features (5)
- visual-representations (5)
- geometric-consistency (5)
- user-interface (5)
- object-detection-models (5)
- model-generalization (5)
- deep-learning-architectures (5)
- controlnet (5)
- neural-architectures (5)
- multi-view-consistency (5)
- commonsense-reasoning (5)
- few-shot-prompting (5)
- multimodal-language-models (5)
- lstm (5)
- gaussian-process (5)
- logistic-regression (5)
- human-ai-collaboration (5)
- global-optimization (5)
- nonconvex-optimization (5)
- variational-inference (5)
- stochastic-optimization (5)
- causal-reasoning (5)
- cross-modal-retrieval (5)
- controllability (5)
- regression-tasks (5)
- view-consistency (5)
- dynamic-objects (5)
- annotation-pipeline (5)
- model-merging (5)
- retrieval-performance (5)
- memory-management (5)
- transliteration (5)
- human-annotations (5)
- mobile-robotics (5)
- word-embeddings (5)
- acquisition-function (5)
- automated-systems (5)
- computational-models (5)
- conversational-agents (5)
- sampling-efficiency (5)
- inverse-reinforcement-learning (5)
- model-optimization (5)
- state-of-the-art-results (5)
- alzheimers-disease (5)
- graph-structure (5)
- small-object-detection (5)
- vision-language-tasks (5)
- visualization (5)
- usability (5)
- data-preprocessing (5)
- performance-analysis (5)
- motion-blur (5)
- molecular-property-prediction (5)
- communication-efficiency (5)
- mamba-architecture (5)
- resource-constraints (5)
- model-behavior (5)
- natural-language-inference (5)
- covariate-shift (5)
- contrastive-language-image-pretraining (5)
- generalization-capability (5)
- bias-reduction (5)
- prompt-tuning (5)
- multi-modal-fusion (5)
- domain-specific-language (5)
- model-bias (5)
- cosine-similarity (5)
- conditional-diffusion-models (5)
- k-means (5)
- intelligibility (4)
- token-generation (4)
- autonomous-robots (4)
- numerical-methods (4)
- scaling-properties (4)
- image-text-retrieval (4)
- artificial-intelligence-generated-content (4)
- simulation-experiments (4)
- high-performance-computing (4)
- black-box-optimization (4)
- heterogeneous-graphs (4)
- segmentation-accuracy (4)
- neural-collapse (4)
- calibration (4)
- singular-value-decomposition (4)
- retrieval-augmentation (4)
- test-time-adaptation (4)
- emotion-recognition (4)
- computational-inefficiencies (4)
- model-uncertainty (4)
- aleatoric-uncertainty (4)
- quantum-neural-networks (4)
- flexibility (4)
- training-loss (4)
- chebyshev-polynomials (4)
- artificial-neural-networks (4)
- data-analytics (4)
- graph-construction (4)
- situational-awareness (4)
- high-energy-physics (4)
- sparse-data (4)
- gaussian-process-regression (4)
- noise-injection (4)
- model-agnostic-methods (4)
- feature-propagation (4)
- clinical-diagnosis (4)
- temporal-resolution (4)
- training-objective (4)
- reasoning-abilities (4)
- artistic-styles (4)
- probabilistic-modeling (4)
- long-range-dependencies (4)
- skip-connections (4)
- harmful-content (4)
- transformer-based-approaches (4)
- open-source-llms (4)
- error-identification (4)
- real-time-interaction (4)
- high-resolution-videos (4)
- partial-observability (4)
- state-space-model (4)
- data-streams (4)
- data-fusion (4)
- image-retrieval (4)
- saliency-maps (4)
- data-management (4)
- optimization-objectives (4)
- noisy-labels (4)
- multi-agent-path-finding (4)
- intelligent-transportation-systems (4)
- feature-extractors (4)
- remote-sensing-data (4)
- lidar-point-clouds (4)
- principal-component-analysis (4)
- image-encoder (4)
- static-analysis (4)
- crowdsourcing (4)
- automated-evaluations (4)
- 3d-scene-generation (4)
- video-datasets (4)
- deblurring (4)
- navigation (4)
- aerial-images (4)
- sampling-steps (4)
- reconstruction-loss (4)
- self-consistency (4)
- training-free-framework (4)
- iterative-refinement (4)
- imagenet-dataset (4)
- object-recognition (4)
- behavioral-patterns (4)
- adversarial-perturbation (4)
- factual-accuracy (4)
- pretrained-language-models (4)
- temporal-correlations (4)
- semantic-consistency (4)
- image-inpainting (4)
- reward-modeling (4)
- prompting-strategies (4)
- mixed-reality (4)
- unmanned-surface-vehicles (4)
- vision-tasks (4)
- training-process (4)
- camera-calibration (4)
- street-view-images (4)
- rendering (4)
- fake-news-detection (4)
- kv-cache (4)
- motion-modeling (4)
- synthetic-training-data (4)
- image-datasets (4)
- human-pose-estimation (4)
- speculative-decoding (4)
- retrieval (4)
- diffusion-based-methods (4)
- video-inpainting (4)
- generative-language-model (4)
- token-pruning (4)
- multilingual-language-models (4)
- visual-instruction-tuning (4)
- nlp-models (4)
- video-question-answering (4)
- quality-of-service (4)
- cost-effectiveness (4)
- representation (4)
- evolutionary-algorithms (4)
- content-creation (4)
- data-complexity (4)
- data-analysis (4)
- public-health (4)
- academic-performance (4)
- path-planning (4)
- expressiveness (4)
- nearest-neighbor-search (4)
- detection-methods (4)
- weather-forecasting (4)
- fairness-metrics (4)
- bi-level-optimization (4)
- cyberattacks (4)
- privacy-utility-trade-off (4)
- wasserstein-distance (4)
- human-preferences (4)
- kullback-leibler-divergence (4)
- visual-foundation-models (4)
- linear-regression (4)
- precision-medicine (4)
- learning-efficiency (4)
- facial-expression-recognition (4)
- vision-and-language-navigation (4)
- low-resolution-images (4)
- image-recognition (4)
- attention-scores (4)
- dynamic-scene-reconstruction (4)
- model-editing (4)
- motion-dynamics (4)
- monocular-cameras (4)
- change-detection (4)
- visual-prompts (4)
- out-of-distribution-data (4)
- computational-pathology (4)
- tokenizer (4)
- dataset-characteristics (4)
- chatbots (4)
- empirical-risk-minimization (4)
- regulatory-compliance (4)
- distributed-training (4)
- optimization-techniques (4)
- automated-framework (4)
- soft-robotics (4)
- time-series-analysis (4)
- traffic-patterns (4)
- graph-learning (4)
- gradient-based-methods (4)
- open-vocabulary-segmentation (4)
- forecasting (4)
- additive-manufacturing (4)
- tool-use (4)
- multi-modal-dataset (4)
- data-acquisition (4)
- differentiable-rendering (4)
- energy-based-models (4)
- video-prediction (4)
- activation-functions (4)
- low-rank-approximation (4)
- masked-image-modeling (4)
- optimization-based-methods (4)
- automatic-detection (4)
- ethical-challenges (4)
- data-driven-models (4)
- text-to-speech (4)
- geometric-structure (4)
- cost-efficiency (4)
- egocentric-video (4)
- long-context-tasks (4)
- data-filtering (4)
- bert-models (4)
- llama-31 (4)
- data-curation (4)
- interpretable-models (4)
- reflection (4)
- data-cleaning (4)
- physical-constraints (4)
- domain-randomization (4)
- environmental-impacts (4)
- cold-start-problem (4)
- low-latency (4)
- root-mean-square-error (4)
- zero-shot-capabilities (4)
- query-generation (4)
- education (4)
- image-compression (4)
- graph-classification (4)
- yolo (4)
- accessibility (4)
- ai-generated-content (4)
- regularization (4)
- conformal-prediction (4)
- experimental-evaluations (4)
- feature-integration (4)
- diversity (4)
- self-correction (4)
- compression-rates (4)
- transformer-layers (4)
- model-scaling (4)
- multimodal-sentiment-analysis (4)
- sim-to-real-gap (4)
- earth-observation-data (4)
- quantitative-analysis (4)
- preference-alignment (4)
- few-shot-examples (4)
- automatic-metrics (4)
- healthcare-applications (4)
- video-synthesis (4)
- graphical-user-interfaces (4)
- multi-turn-dialogues (4)
- vision-language-action-model (4)
- sentiment-classification (4)
- mlp (4)
- neuromorphic-computing (4)
- intrinsic-rewards (4)
- deeponet (4)
- disentanglement (4)
- user-generated-content (4)
- human-judgments (4)
- multimodal-information (4)
- diagnostic-performance (4)
- engagement (4)
- semantic-representations (4)
- open-source-tools (4)
- annotations (4)
- computation-costs (4)
- fraud-detection (4)
- backpropagation (4)
- memory-usage (4)
- instruction-fine-tuning (4)
- optimization-process (4)
- high-dimensional-spaces (4)
- error-correction (4)
- ai-in-education (4)
- human-ai-interaction (4)
- kl-divergence (4)
- ai-safety (4)
- adversarial-prompts (4)
- state-estimation (4)
- shap (4)
- language-understanding (4)
- uncertainty-modeling (4)
- robustness-analysis (4)
- video-quality (4)
- 3d-segmentation (4)
- real-world-tasks (4)
- spatial-information (4)
- parameter-efficiency (4)
- ensemble-models (4)
- collaboration (4)
- temporal-scales (4)
- real-time-deployments (4)
- few-shot-class-incremental-learning (4)
- text-encoders (4)
- model-efficiency (4)
- self-supervision (4)
- answer-generation (4)
- graphics (4)
- inverse-kinematics (4)
- psnr (4)
- molecular-structures (4)
- latent-features (4)
- reasoning-ability (4)
- visual-inertial-odometry (4)
- neural-model (4)
- fine-tuning-strategy (4)
- multiclass-classification (4)
- benchmark-development (4)
- image-text-pairs (4)
- stock-price-prediction (4)
- bayesian-deep-learning (4)
- cross-validation (4)
- clinical-trials (4)
- distillation (4)
- physically-based-rendering (4)
- linear-models (4)
- fine-tuning-methods (4)
- visual-generation (4)
- visual-understanding (4)
- large-language-models-llms (4)
- data-distribution (4)
- ethical-concerns (4)
- preference-learning (4)
- cross-domain-generalization (4)
- 3d-vision (4)
- modality-gap (4)
- statistical-models (4)
- global-attention-mechanism (4)
- sensitive-information (4)
- clinical-decision-support (4)
- robot-manipulation (4)
- generative-priors (4)
- training-strategies (4)
- gaming (4)
- inertial-measurement-units (4)
- human-object-interactions (4)
- prompt-compression (4)
- linear-programming (4)
- memory-mechanism (4)
- model-design (4)
- matrix-factorization (4)
- perplexity (4)
- optimal-control (4)
- parameterized-quantum-circuits (4)
- diagnostics (4)
- knowledge-representation (4)
- qualitative-analysis (4)
- empirical-studies (4)
- multilingual-dataset (4)
- training-framework (4)
- fine-tuned-models (4)
- text-to-speech-systems (3)
- monte-carlo-simulations (3)
- mmlu (3)
- spatial-understanding (3)
- mimic-iv-database (3)
- multi-robot-systems (3)
- safety-mechanisms (3)
- neuroscience (3)
- multimodal-integration (3)
- sampling-strategy (3)
- user-interests (3)
- metaverse (3)
- energy (3)
- privacy-issues (3)
- integrated-sensing-and-communication (3)
- data-sharing (3)
- burgers-equation (3)
- risk-factors (3)
- safety-and-reliability (3)
- simulation-environments (3)
- multi-armed-bandits (3)
- vehicle-routing-problems (3)
- hybrid-methods (3)
- vector-databases (3)
- hardware-experiments (3)
- prediction-tasks (3)
- scientific-research (3)
- engineering-applications (3)
- large-models (3)
- local-training (3)
- automated-driving-systems (3)
- relational-databases (3)
- reservoir-computing (3)
- policy-network (3)
- tactile-sensing (3)
- 3d-geometry (3)
- personalized-learning (3)
- modular-design (3)
- decision-transformers (3)
- parameter-reduction (3)
- mixed-integer-programming (3)
- hypothesis-testing (3)
- benchmark-tasks (3)
- prompting (3)
- spatio-temporal-information (3)
- molecular-properties (3)
- rectified-flow-model (3)
- memory-demands (3)
- right-to-be-forgotten (3)
- quantum-circuits (3)
- fault-diagnosis (3)
- convergence-analysis (3)
- protein-engineering (3)
- autoregressive-generation (3)
- internal-representations (3)
- task-adaptation (3)
- computational-cost-reduction (3)
- interpretation (3)
- data-exploration (3)
- big-data (3)
- ai-applications (3)
- copyright-infringement (3)
- human-robot-collaboration (3)
- user-studies (3)
- gesture-recognition (3)
- adversarial-samples (3)
- mean-absolute-error (3)
- classifier (3)
- feature-transformation (3)
- human-vision (3)
- fast-fourier-transform (3)
- dataset-shift (3)
- streaming-data (3)
- concept-drift (3)
- self-supervised-foundation-models (3)
- stylegan (3)
- fid-score (3)
- node-representations (3)
- outliers (3)
- tracking (3)
- vector-symbolic-architectures (3)
- security-concerns (3)
- depth-sensors (3)
- model-inference (3)
- generative-techniques (3)
- fine-tuning-strategies (3)
- large-reconstruction-models (3)
- resampling (3)
- video-generation-models (3)
- object-detectors (3)
- visual-explanations (3)
- diffusion-priors (3)
- secure-multi-party-computation (3)
- video-generation-quality (3)
- multimodal-fusion (3)
- transformer-based-methods (3)
- geometry (3)
- feature-alignment (3)
- synthetic-aperture-radar-sar (3)
- photorealistic-rendering (3)
- geometry-recovery (3)
- linear-probing (3)
- mean-squared-error (3)
- knowledge-retention (3)
- camera-parameters (3)
- arvr (3)
- feature-similarity (3)
- video-anomaly-detection (3)
- face-detection (3)
- single-image (3)
- visual-slam (3)
- large-multi-modal-models (3)
- radiology (3)
- actionable-insights (3)
- motion-prediction (3)
- cross-entropy-loss (3)
- real-time-feedback (3)
- resource-constrained-edge-devices (3)
- statistical-heterogeneity (3)
- discriminative-tasks (3)
- 3d-models (3)
- personalized-image-generation (3)
- reference-images (3)
- image-to-image-translation (3)
- perceptual-metrics (3)
- adversarial-patches (3)
- control (3)
- image-tokenization (3)
- detection-transformer (3)
- score-matching (3)
- object-manipulation (3)
- discrete-cosine-transform (3)
- dataset-distillation (3)
- motion-editing (3)
- urban-planning (3)
- feature-interactions (3)
- ai-technologies (3)
- predictive-uncertainty (3)
- ultrasound-images (3)
- consistency (3)
- posterior-sampling (3)
- natural-images (3)
- model-reliability (3)
- lightweight-models (3)
- graph-network (3)
- safety-benchmarks (3)
- knowledge-intensive-tasks (3)
- semantic-information-extraction (3)
- monolingual-models (3)
- outlier-detection (3)
- hybrid-architectures (3)
- sequence-to-sequence-model (3)
- synonymy (3)
- semantic-relations (3)
- reconstruction-accuracy (3)
- parameterization (3)
- end-to-end-learning (3)
- dit (3)
- speedup (3)
- cross-entropy (3)
- multi-stage-training (3)
- mixture-of-experts-architecture (3)
- training-costs (3)
- user-satisfaction (3)
- reading-comprehension (3)
- image-diffusion-models (3)
- feature-distributions (3)
- performance-optimization (3)
- imaging-modalities (3)
- intra-class-diversity (3)
- attack-effectiveness (3)
- systematic-review (3)
- limitations (3)
- optimization-strategies (3)
- human-mesh-recovery (3)
- diffusion-based-approach (3)
- contextual-features (3)
- value-function (3)
- model-performance-evaluation (3)
- 4d-reconstruction (3)
- generalization-abilities (3)
- natural-language-query (3)
- annotation-costs (3)
- knowledge-graph-embedding (3)
- vision-language-alignment (3)
- generative-llms (3)
- fine-grained-classification (3)
- 3d-reconstruction-models (3)
- modularity (3)
- oversmoothing (3)
- large-scale-graphs (3)
- object-removal (3)
- dual-branch-architecture (3)
- high-quality-reconstruction (3)
- resource-constrained-applications (3)
- visual-navigation (3)
- reranking (3)
- 3d-consistency (3)
- training-instability (3)
- demonstration-selection (3)
- joint-optimization (3)
- 3d-generation (3)
- noisy-datasets (3)
- cognition (3)
- encoder-decoder-architectures (3)
- exact-algorithms (3)
- threat-models (3)
- influence-maximization (3)
- actor-critic-architecture (3)
- benchmark-experiments (3)
- distributed-computing (3)
- big-data-analytics (3)
- finance (3)
- multi-class-classifier (3)
- social-dynamics (3)
- methodologies (3)
- optimal-control-problems (3)
- heuristics (3)
- squeeze-and-excitation-blocks (3)
- hyperparameter-selection (3)
- spatiotemporal-patterns (3)
- divide-and-conquer-strategy (3)
- graph-attention-networks (3)
- distributed-optimization (3)
- unstructured-data (3)
- design-space-exploration (3)
- computational-advantages (3)
- disease-prediction (3)
- common-sense-reasoning (3)
- surface-normals (3)
- memory-overhead (3)
- colorectal-cancer (3)
- machine-vision (3)
- feature-diversity (3)
- interpretable-features (3)
- geometric-optimization (3)
- polyp-segmentation (3)
- feature-aggregation (3)
- uavs (3)
- swin-transformer (3)
- privacy-preserving-methods (3)
- gene-expression-prediction (3)
- 3d-content-creation (3)
- educational-assessment (3)
- spectral-features (3)
- embodied-agents (3)
- feature-pyramid (3)
- imbalanced-datasets (3)
- error-detection (3)
- sparse-views (3)
- kitti-360-dataset (3)
- clip-features (3)
- memory-complexity (3)
- species-identification (3)
- translation (3)
- conditional-variational-autoencoder (3)
- object-segmentation (3)
- multimodal-architectures (3)
- risk-management (3)
- feature-correlations (3)
- natural-language-queries (3)
- rgb-d-cameras (3)
- environmental-conditions (3)
- future-directions (3)
- cityscapes (3)
- camera-control (3)
- parallelization (3)
- 3d-shapes (3)
- autoregressive-transformers (3)
- environmental-sustainability (3)
- offline-reinforcement-learning (3)
- visual-attributes (3)
- false-positive-rate (3)
- re-ranking (3)
- passage-retrieval (3)
- user-trust (3)
- robotic-systems (3)
- uncrewed-aerial-vehicles (3)
- gnss-denied-environments (3)
- conditional-sampling (3)
- physical-principles (3)
- model-update (3)
- communication-overhead (3)
- output-quality (3)
- kv-cache-compression (3)
- flashattention (3)
- np-hardness (3)
- neural-ordinary-differential-equations (3)
- diffusion-based-generative-model (3)
- multi-modal-learning (3)
- disease-diagnosis (3)
- surveillance (3)
- pretraining-datasets (3)
- pseudo-labeling (3)
- clinical-notes (3)
- model-fairness (3)
- representation-quality (3)
- inverse-rendering (3)
- ray-tracing (3)
- volume-rendering (3)
- spatial-coherence (3)
- earth-observation (3)
- adversarial-noise (3)
- concept-learning (3)
- cost-reduction (3)
- point-cloud-data (3)
- automated-metrics (3)
- dense-prediction-tasks (3)
- convolutional-layers (3)
- defect-detection (3)
- video-editing (3)
- distillation-method (3)
- fine-tuning-techniques (3)
- sparse-point-clouds (3)
- dataset-generation (3)
- event-based-cameras (3)
- captioning (3)
- evaluation-process (3)
- dialogue-generation (3)
- linguistic-diversity (3)
- 3d-datasets (3)
- continuous-optimization (3)
- benchmark-suite (3)
- explainability-methods (3)
- attention-maps (3)
- reasoning-accuracy (3)
- copyright-protection (3)
- question-answer-pairs (3)
- fast-inference (3)
- neural-representations (3)
- nonlinear-relationships (3)
- dynamic-mode-decomposition (3)
- particle-physics (3)
- ridge-regression (3)
- gpt-35 (3)
- bidirectional-long-short-term-memory (3)
- theoretical-results (3)
- personalized-treatment (3)
- practical-applications (3)
- molecular-dynamics (3)
- diffusion-processes (3)
- privacy-preserving-solutions (3)
- physical-systems (3)
- control-algorithms (3)
- robotics-applications (3)
- post-training-quantization (3)
- trajectory-generation (3)
- data-driven-methods (3)
- fully-connected-neural-network (3)
- automated-detection (3)
- motion-artifacts (3)
- community-detection (3)
- discrete-wavelet-transform (3)
- heterogeneity (3)
- optimization-framework (3)
- realism (3)
- traffic-signal-control (3)
- ethical-implications (3)
- text-generation-models (3)
- score-based-diffusion-models (3)
- high-resolution-image-generation (3)
- graph-convolutions (3)
- knowledge-graph-completion (3)
- memory (3)
- motion-retargeting (3)
- mri-data (3)
- image-fusion (3)
- hypernetworks (3)
- multi-modal-understanding (3)
- privacy-breaches (3)
- audio-lip-synchronization (3)
- facial-expressions (3)
- transformer-decoder (3)
- video-generative-models (3)
- recognition-accuracy (3)
- loss-landscapes (3)
- document-ai (3)
- computational-requirements (3)
- memory-requirements (3)
- feature-fusion (3)
- medical-datasets (3)
- computational-chemistry (3)
- structural-integrity (3)
- expert-models (3)
- simulators (3)
- odometry (3)
- text-guided-image-editing (3)
- stereo-matching (3)
- concept-bottleneck-models (3)
- e-commerce (3)
- generalization-problems (3)
- agent-performance (3)
- language-barriers (3)
- real-time-object-detection (3)
- performance-benchmarking (3)
- probability-theory (3)
- long-videos (3)
- video-benchmarks (3)
- code-quality (3)
- gpu-utilization (3)
- computational-bottlenecks (3)
- monocular-slam (3)
- pretrained-llms (3)
- machine-learning-applications (3)
- invertible-transformation (3)
- graph-transformer (3)
- dynamic-programming (3)
- global-optimisation (3)
- composite-loss-functions (3)
- fall-detection (3)
- relu-neural-networks (3)
- gpu-training (3)
- scientific-machine-learning (3)
- survival-analysis (3)
- sharpness-aware-minimization (3)
- generative-capabilities (3)
- throughput (3)
- video-quality-assessment (3)
- generalisation (3)
- cifar-100 (3)
- diagnosis (3)
- object-representations (3)
- image-and-text-embeddings (3)
- affine-transformations (3)
- conditional-generative-model (3)
- facial-features (3)
- point-tracking (3)
- feature-maps (3)
- sparse-attention (3)
- video-object-segmentation (3)
- infrared-images (3)
- image-annotations (3)
- data-contamination (3)
- fact-checking (3)
- document-understanding (3)
- dataset-size (3)
- 2d-foundation-models (3)
- memory-reduction (3)
- chest-x-rays (3)
- multimodal-capabilities (3)
- sensitivity (3)
- domain-specific-tasks (3)
- reasoning-tasks (3)
- pearson-correlation-coefficient (3)
- gradient-flow (3)
- finite-element-method (3)
- hierarchical-structure (3)
- quadratic-programming (3)
- navier-stokes-equations (3)
- electrocardiograms (3)
- finite-state-machine (3)
- zero-shot-inference (3)
- optimization-tasks (3)
- ethical-issues (3)
- safety-constraints (3)
- function-approximation (3)
- jailbreaking (3)
- forecasting-models (3)
- distribution-mismatch (3)
- policy-improvement (3)
- embedding-generation (3)
- curse-of-dimensionality (3)
- traditional-chinese-medicine (3)
- differential-equations (3)
- gradient-based-optimization (3)
- counterfactual-explanations (3)
- data-access (3)
- compositionality (3)
- knowledge-extraction (3)
- pre-training-methods (3)
- conversational-ai (3)
- neural-operator (3)
- neurodegenerative-diseases (3)
- aggregation-algorithms (3)
- synthetic-images (3)
- fake-news (3)
- multi-modal-reasoning (3)
- trainable-parameters (3)
- visual-place-recognition (3)
- semantic-structure (3)
- 3d-editing (3)
- multimodal-generation (3)
- offline-rl (3)
- multimodal-inputs (3)
- compressed-sensing (3)
- sample-generation (3)
- real-time-inference (3)
- memory-costs (3)
- transformer-based-language-models (3)
- data-retrieval (3)
- semantic-correlations (3)
- vision-language-pre-training (3)
- partially-observable-environments (3)
- world-knowledge (3)
- sample-quality (3)
- trustworthy-ai (3)
- 3d-content-generation (3)
- geometric-details (3)
- text-image-alignment (3)
- dynamic-analysis (3)
- heuristic-search (3)
- cross-modal-matching (3)
- mitigation-strategies (3)
- speech-synthesis (3)
- meta-evaluation (3)
- formal-verification (3)
- instruction-following (3)
- data-selection (3)
- data-redundancy (3)
- semantic-search (3)
- knowledge-acquisition (3)
- time-series-tasks (3)
- video-frame-interpolation (3)
- cross-modality-alignment (3)
- medical-applications (3)
- ssim (3)
- sequential-monte-carlo (3)
- dynamic-graphs (3)
- t5-model (3)
- network-architectures (3)
- tensorflow (3)
- prompting-techniques (3)
- automatic-evaluations (3)
- encoders (3)
- baseline-methods (3)
- future-research-directions (3)
- unstructured-pruning (3)
- text-detection (3)
- visualization-tools (3)
- parallel-computing (3)
- extended-reality (3)
- image-priors (3)
- gpu-acceleration (3)
- computational-speed (3)
- task-complexity (3)
- interactive-visualizations (3)
- urban-mobility (3)
- multilingual-data (3)
- decoder (3)
- human-llm-interaction (3)
- multi-step-reasoning (3)
- model-calibration (3)
- classification-problems (3)
- non-iid-data (3)
- performance-evaluation-metrics (3)
- contrastive-language-image-pre-training (3)
- code-comprehension (3)
- text (3)
- facial-images (3)
- nash-equilibrium (3)
- watermarking (3)
- end-to-end-training (3)
- encoder-decoder-models (3)
- error-reduction (3)
- gpt-2 (3)
- pre-training-corpus (3)
- compression-methods (3)
- vision-models (3)
- program-synthesis (3)
- qualitative-evaluations (3)
- human-machine-interaction (3)
- spatial-attention (3)
- panoptic-segmentation (3)
- lidar-segmentation (3)
- token-compression (3)
- zero-shot-transfer (3)
- classical-machine-learning (3)
- long-video-generation (3)
- control-policies (3)
- annotation-quality (3)
- annotation-guidelines (3)
- annotated-data (3)
- electroencephalogram (3)
- stochastic-differential-equation (3)
- attention-weights (3)
- denoising-diffusion-probabilistic-models (3)
- 3d-printing (3)
- miou (3)
- gpt-4o-mini (3)
- speech-recognition (3)
- model-weights (3)
- heterogeneous-data (3)
- training-accuracy (3)
- lateral-thinking (3)
- multi-agent-framework (3)
- gaze-estimation (3)
- multilingual-large-language-models (3)
- forecasting-accuracy (3)
- black-box-methods (3)
- acoustic-features (3)
- prosody (3)
- mel-spectrograms (3)
- synthetic-aperture-radar (3)
- multi-modal-alignment (3)
- graph-contrastive-learning (3)
- semantic-constraints (3)
- llama-3 (3)
- depth-perception (3)
- prompting-strategy (3)
- activation-patterns (3)
- information-bottleneck (3)
- data-scaling (3)
- long-horizon-planning (3)
- multi-camera-systems (3)
- local-features (3)
- high-resource-languages (3)
- multi-view-information (3)
- iteration-complexity (3)
- content-preservation (3)
- generalization-error (3)
- visual-reasoning (3)
- image-enhancement (3)
- t-sne (3)
- model-development (3)
- intelligent-agents (3)
- data-perturbations (3)
- open-source-toolkit (3)
- response-quality (3)
- continuous-monitoring (3)
- video-summarization (3)
- motion-deblurring (3)
- action-recognition (3)
- conditional-average-treatment-effects (3)
- training (3)
- downstream-applications (3)
- downstream-performance (3)
- transformer-framework (3)
- temporal-redundancy (3)
- attention-heads (3)
- scientific-literature (3)
- negative-log-likelihood (3)
- stance-detection (3)
- collaborative-decision-making (3)
- lipschitz-continuity (3)
- genetic-programming (3)
- model-integrity (3)
- image-transformations (3)
- unlearning-methods (3)
- answer-set-programming (3)
- materials-discovery (3)
- zero-shot-generation (3)
- privacy-leakage (3)
- prompt-optimization (3)
- lossy-compression (3)
- speech-processing (3)
- structural-causal-models (3)
- deep-networks (3)
- resource-consumption (3)
- long-term-dependencies (3)
- vision-language-pretraining (3)
- multitask-learning (3)
- auroc (3)
- multi-modal-models (3)
- mapping (3)
- multi-modal-information (3)
- motion-generation (3)
- processing-time (3)
- temperature-scaling (3)
- compression-techniques (3)
- cross-lingual-transfer (3)
- social-biases (3)
- perceptual-quality (3)
- large-scale-networks (3)
- simulated-datasets (3)
- system-performance (3)
- dynamic-systems (3)
- performance-disparities (3)
- heterogeneous-data-distributions (3)
- predictive-maintenance (3)
- drug-discovery (3)
- traceability (3)
- real-time-data-processing (3)
- audio-generation (3)
- inference (3)
- llama2-7b (3)
- parameter-tuning (3)
- structured-pruning (3)
- temporal-alignment (3)
- recommendation-accuracy (3)
- geometric-understanding (3)
- python-api (3)
- landmark-detection (3)
- multi-view-inconsistency (3)
- mean-average-precision (3)
- statistical-analyses (3)
- byte-pair-encoding (3)
- local-structures (3)
- histopathology (3)
- flat-minima (3)
- motivational-interviewing (3)
- digital-pathology (3)
- biomarkers (3)
- probabilistic-framework (3)
- token-reduction (3)
- black-box-setting (3)
- algorithm-selection (3)
- spatial-heterogeneity (2)
- linear-discriminant-analysis (2)
- numerical-integration (2)
- pdes (2)
- gsm8k-benchmarks (2)
- multi-label-classification (2)
- data-structure (2)
- search-efficiency (2)
- topological-graph (2)
- task-diversity (2)
- predictive-power (2)
- temporal-convolutional-networks (2)
- ablation-analysis (2)
- sars-cov-2 (2)
- boundary-conditions (2)
- spatial-and-temporal-dependencies (2)
- temporal-dependency (2)
- weak-supervision (2)
- human-ai-cooperation (2)
- manufacturing (2)
- security-issues (2)
- transportation (2)
- convex-problem (2)
- generalized-additive-models (2)
- carla-simulator (2)
- sampling-based-methods (2)
- problem-variants (2)
- dual-attention-mechanism (2)
- feedforward-neural-networks (2)
- bit-rates (2)
- decision-support-systems (2)
- modality-specific-features (2)
- manifolds (2)
- wireless-communication (2)
- resource-optimization (2)
- parallelism (2)
- wind-turbines (2)
- user-needs (2)
- beam-search (2)
- adversarial-modification (2)
- architectural-choices (2)
- bilevel-optimization (2)
- robotic-manipulators (2)
- sensor-localization (2)
- contact-localization (2)
- learning-strategies (2)
- robot-design (2)
- computational-pipeline (2)
- chemical-space (2)
- lipid-nanoparticles (2)
- ionizable-lipids (2)
- unsupervised-framework (2)
- model-free-settings (2)
- information-theoretic-bounds (2)
- mujoco (2)
- game-theory (2)
- computational-experiments (2)
- task-specific-fine-tuning (2)
- sampling-process (2)
- minimum-description-length-principle (2)
- sample-selection (2)
- structure-based-drug-design (2)
- hypergraph-neural-networks (2)
- higher-order-methods (2)
- neural-odes (2)
- siamese-networks (2)
- heterogeneous-data-sources (2)
- data-uncertainty (2)
- fault-detection (2)
- vibration-signals (2)
- numerical-results (2)
- cifar10 (2)
- cnn-based-models (2)
- approximation-methods (2)
- query-complexity (2)
- distance-functions (2)
- restricted-boltzmann-machines (2)
- collaborative-filtering (2)
- immunotherapy (2)
- biophysics (2)
- abstract-reasoning (2)
- multi-step-planning (2)
- boolean-functions (2)
- neural-architecture-search (2)
- public-trust (2)
- future-research (2)
- computation-efficiency (2)
- differential-flatness (2)
- langchain (2)
- program-generation (2)
- user-centered-design (2)
- long-short-term-memory-network (2)
- high-dimensional-optimization (2)
- human-machine-interfaces (2)
- task-efficiency (2)
- black-box-scenarios (2)
- privacy-auditing (2)
- autonomous-penetration-testing (2)
- control-systems (2)
- volumetric-imaging (2)
- dynamic-processes (2)
- decision-making-processes (2)
- sex-classification (2)
- binary-neural-networks (2)
- compositional-reasoning (2)
- video-large-language-models (2)
- productivity (2)
- temporal-understanding (2)
- message-passing (2)
- graph-learning-tasks (2)
- hybrid-approach (2)
- scene-generation (2)
- lesion-detection (2)
- in-memory-computing (2)
- limit-cycles (2)
- influence-functions (2)
- scene-reconstruction-quality (2)
- egocentric-perception (2)
- gelu (2)
- softmax (2)
- adaptive-approaches (2)
- image-codec (2)
- evolutionary-game-theory (2)
- light-curves (2)
- filtering-techniques (2)
- physical-interactions (2)
- two-stage-framework (2)
- resnet-architecture (2)
- secure-aggregation (2)
- program-analysis (2)
- scientific-reasoning (2)
- hypothesis-evaluation (2)
- maximum-mean-discrepancy (2)
- deformation (2)
- nerf (2)
- task-oriented-communication (2)
- textual-descriptions (2)
- 2d-gaussian-splatting (2)
- video-understanding-benchmarks (2)
- audio-modality (2)
- trajectory-data (2)
- sycophancy (2)
- ranks (2)
- multimodality (2)
- personalized-information (2)
- realistic-avatars (2)
- animatable-avatars (2)
- reward-shaping (2)
- image-features (2)
- privacy-risk (2)
- 3d-imaging (2)
- video-instance-segmentation (2)
- multiple-object-tracking (2)
- nonlinear-dynamics (2)
- few-shot-image-classification (2)
- jacobian-matrix (2)
- perturbation-optimization (2)
- documentation (2)
- differentiable-optimization (2)
- video-segmentation (2)
- flow-models (2)
- concept-removal (2)
- continuous-action-spaces (2)
- policy-modeling (2)
- training-schemes (2)
- latency-constraints (2)
- feature-optimization (2)
- autonomous-driving-simulator (2)
- self-attention-layers (2)
- model-personalization (2)
- global-knowledge (2)
- demographic-bias (2)
- cvpr-2024 (2)
- wildfire-prediction (2)
- progressive-training (2)
- artistic-images (2)
- human-perception (2)
- model-adaptability (2)
- false-positives (2)
- hand-gesture-recognition (2)
- high-performance-system (2)
- driving-simulations (2)
- pandaset (2)
- photo-realistic-rendering (2)
- nuscenes (2)
- cnn-classifier (2)
- training-recipes (2)
- unit-tests (2)
- generalist-policy (2)
- stochastic-algorithms (2)
- prediction-reliability (2)
- generalization-to-novel-objects (2)
- self-attention-maps (2)
- in-context-generation (2)
- image-generation-tasks (2)
- edge-networks (2)
- device-heterogeneity (2)
- spatial-intelligence (2)
- peak-signal-to-noise-ratio (2)
- detection-tools (2)
- linear-inverse-problems (2)
- humanml3d-dataset (2)
- hierarchical-framework (2)
- robot-task-planning (2)
- dataset-biases (2)
- task-decomposition (2)
- workflow-generation (2)
- rescaling (2)
- discrete-data (2)
- layout-generation (2)
- shap-scores (2)
- explanation-generation (2)
- sequential-learning (2)
- computer-vision-applications (2)
- natural-language-prompts (2)
- ffhq-dataset (2)
- novel-dataset (2)
- point-cloud-registration (2)
- camera-tracking (2)
- recognition-performance (2)
- backdoor-removal (2)
- shapenet-datasets (2)
- population-dynamics (2)
- reasoning-capability (2)
- point-cloud-processing (2)
- retrieval-augmentation-generation (2)
- problem-solving-capabilities (2)
- yolo-models (2)
- monte-carlo-sampling (2)
- mutual-learning (2)
- text-mining (2)
- nlp-research (2)
- human-translation (2)
- cross-cultural-differences (2)
- ethical-deployment (2)
- gender-bias (2)
- parallel-data (2)
- baseline-comparison (2)
- training-time-reduction (2)
- markov-chains (2)
- precipitation-nowcasting (2)
- self-supervised-models (2)
- rule-based-approach (2)
- disease-progression (2)
- tracking-techniques (2)
- gene-expression-profiles (2)
- hypernymy (2)
- hyponymy (2)
- temporal-sequence (2)
- 2d-keypoints (2)
- local-details (2)
- rnns (2)
- robust-evaluation (2)
- southeast-asian-languages (2)
- inference-overhead (2)
- disease-classification (2)
- multimodal-aspect-based-sentiment-analysis (2)
- deployment-costs (2)
- routing-mechanisms (2)
- ab-testing (2)
- relevance-modeling (2)
- continual-pre-training (2)
- multimodal-llms (2)
- memory-bandwidth (2)
- activation-sparsity (2)
- part-segmentation (2)
- semantic-scene-completion (2)
- combined-loss-function (2)
- high-frequency-components (2)
- vision-state-space-module (2)
- incremental-mapping (2)
- hyper-parameters (2)
- mesh-reconstruction (2)
- urban-scene-datasets (2)
- neural-scene-reconstruction (2)
- event-based-methods (2)
- constraint-satisfaction-problems (2)
- graph-coloring (2)
- controllable-generation (2)
- scene-manipulation (2)
- fusion-strategies (2)
- communication-strategies (2)
- spatiotemporal-relationships (2)
- visual-token-pruning (2)
- social-interactions (2)
- pretrained-vision-models (2)
- robot-manipulator (2)
- constraint-satisfaction (2)
- biobert (2)
- sequential-data (2)
- algorithm-development (2)
- demographic-fairness (2)
- language-agent (2)
- spatio-temporal-data (2)
- animal-pose-estimation (2)
- biomechanics (2)
- shape-estimation (2)
- semantic-gap (2)
- gui-agents (2)
- skin-lesion-segmentation (2)
- cnn-architectures (2)
- multilingual-contexts (2)
- model-agnostic-meta-learning (2)
- depth-wise-convolutions (2)
- cnn-based-methods (2)
- object-reconstruction (2)
- tuning-free-approaches (2)
- multi-granularity-segmentation (2)
- training-set (2)
- sampling-methods (2)
- multi-modal-augmentations (2)
- linear-time-complexity (2)
- interaction (2)
- vision-understanding (2)
- 3d-computer-vision (2)
- token-merging (2)
- inference-throughput (2)
- embodied-question-answering (2)
- self-attention-module (2)
- retrieval-tasks (2)
- two-stage-training-strategy (2)
- multimodal-information-retrieval (2)
- computational-challenges (2)
- geometric-information (2)
- multi-object-tracking (2)
- rectified-flow-framework (2)
- rectified-flow-transformers (2)
- multi-modal-setting (2)
- mmdit-architecture (2)
- llama-model (2)
- radiance-fields (2)
- action-classification (2)
- bug-localization (2)
- bug-fixing (2)
- temporal-grounding (2)
- quantization-error (2)
- optimization-strategy (2)
- self-driving-vehicles (2)
- artificial-intelligence-integration (2)
- directed-graphs (2)
- synthetic-examples (2)
- social-welfare (2)
- redundancy-reduction (2)
- predictor (2)
- intensive-care-units (2)
- adversarial-networks (2)
- a-search (2)
- viral-marketing (2)
- model-interpretation (2)
- filtered-backprojection (2)
- learning-based-method (2)
- policy-recommendations (2)
- machine-learning-tasks (2)
- feature-consistency (2)
- system-robustness (2)
- graph-partitioning (2)
- student-learning (2)
- feedback-mechanisms (2)
- classification-outcomes (2)
- automatic-prompt-optimization (2)
- spatial-decision-making (2)
- robot-operating-system (2)
- compliance (2)
- dropout-regularization (2)
- physics-driven-model (2)
- parametric-convergence-rate (2)
- k-means-algorithm (2)
- exploration-exploitation-trade-offs (2)
- smart-contracts (2)
- blockchain (2)
- auc (2)
- technical-features (2)
- multi-view-clustering (2)
- model-stability (2)
- environment (2)
- epidemiology (2)
- information-theory (2)
- learning-dynamics (2)
- pareto-set (2)
- black-box-objective-functions (2)
- information-sharing (2)
- traffic-congestion (2)
- bias-detection (2)
- smart-cities (2)
- trustworthy-systems (2)
- intrusion-detection-system (2)
- simulation-based-testing (2)
- explainable-recommendation (2)
- arithmetic-circuits (2)
- ai-planning (2)
- healthcare-costs (2)
- interactive-user-interface (2)
- pattern-recognition (2)
- plant-disease-detection (2)
- precision-agriculture (2)
- optimizers (2)
- minority-class (2)
- high-dimensional-datasets (2)
- crop-segmentation (2)
- satellite-image-time-series (2)
- single-photon-avalanche-diodes (2)
- intelligent-systems (2)
- aircraft-detection (2)
- semantic-awareness (2)
- key-information-extraction (2)
- document-images (2)
- photorealism (2)
- visual-generative-tasks (2)
- script-generation (2)
- naive-bayes (2)
- diabetic-retinopathy (2)
- consistency-regularization (2)
- data-replay (2)
- global-navigation-satellite-system (2)
- search-and-rescue (2)
- u-net-architecture (2)
- x-ray-images (2)
- diagnostic-process (2)
- multimodal-representations (2)
- patient-outcomes (2)
- posterior-distribution (2)
- synthesis (2)
- vision-tokenizers (2)
- high-dimensional-latent-spaces (2)
- shadow-removal (2)
- hyperspectral-images (2)
- spatial-features (2)
- user-engagement (2)
- llm-hallucination (2)
- efficientnet (2)
- customization (2)
- misalignment (2)
- score-distillation-sampling (2)
- language-embeddings (2)
- token-retention (2)
- pretrained-vision-language-models (2)
- empirical-study (2)
- 4d-representation (2)
- gaussian-representations (2)
- image-generation-quality (2)
- wavelet-transform (2)
- knowledge-localization (2)
- shadows (2)
- pascal-voc-datasets (2)
- token-embeddings (2)
- discourse-analysis (2)
- cross-modal-fusion (2)
- inter-agent-communication (2)
- computational-notebooks (2)
- security-threats (2)
- tabular-data-generation (2)
- robotic-platform (2)
- stereo-cameras (2)
- domain-specific-models (2)
- dynamic-interactions (2)
- classification-datasets (2)
- retention-rate (2)
- training-approach (2)
- training-methods (2)
- photorealistic-images (2)
- graph-neural-architecture-search (2)
- entropy-minimization (2)
- coarse-to-fine-modeling (2)
- latent-tokens (2)
- residual-quantization (2)
- llm-architectures (2)
- rlhf (2)
- self-improvement-algorithms (2)
- probabilistic-interpretation (2)
- euclidean-distances (2)
- language-instruction (2)
- semantic-knowledge (2)
- scene-layout-representation (2)
- carbon-emissions (2)
- ai-feedback (2)
- realistic-movements (2)
- text-video-alignment (2)
- boundary-information (2)
- bias-in-datasets (2)
- dataset-development (2)
- false-negative-rate (2)
- citation-generation (2)
- fault-classification (2)
- severity-classification (2)
- item-response-theory (2)
- forecasting-methods (2)
- rmse (2)
- ai-research (2)
- stakeholders (2)
- gradient-clipping (2)
- heart-disease-prediction (2)
- particle-swarm-optimization (2)
- stability-guarantees (2)
- koopman-operator-theory (2)
- lyapunov-functions (2)
- failure-detection (2)
- batch-normalization (2)
- gradient-boosting (2)
- iot-devices (2)
- position-control (2)
- thompson-sampling (2)
- information-theoretic-framework (2)
- constraints (2)
- aerodynamics (2)
- causal-modeling-framework (2)
- specifications (2)
- generalization-properties (2)
- robustness-enhancement (2)
- foundational-model (2)
- problem-solving (2)
- supervised-models (2)
- spatio-temporal-graph-neural-networks (2)
- fault-tolerance (2)
- mobility (2)
- validation (2)
- clustering-algorithms (2)
- electroencephalography (2)
- sparsity-inducing-priors (2)
- learning-augmented-algorithms (2)
- approximation-algorithms (2)
- robot-locomotion (2)
- omnidirectional-mobility (2)
- hilbert-spaces (2)
- category-theory (2)
- numerical-examples (2)
- educational-technology (2)
- feedback (2)
- real-time-control (2)
- open-set-environments (2)
- portrait-image-animation (2)
- generative-diffusion-model (2)
- guidance-scale (2)
- parameter-optimization (2)
- computational-fluid-dynamics (2)
- software-testing (2)
- full-parameter-fine-tuning (2)
- low-rank-representations (2)
- artificial-intelligence-models (2)
- spatial-dependencies (2)
- gradient-checkpointing (2)
- accuracy-and-speed-trade-off (2)
- text-rewriting (2)
- data-valuation (2)
- bias-mitigation-techniques (2)
- task-space (2)
- label-imbalance (2)
- unsupervised-3d-representation-learning (2)
- energy-barrier (2)
- telemedicine (2)
- mobilenet (2)
- parametric-models (2)
- source-free-domain-adaptation (2)
- semi-supervised-domain-adaptation (2)
- scaled-dot-product-attention (2)
- visual-anomaly-detection (2)
- quantitative-comparisons (2)
- 3d-environment (2)
- training-speed (2)
- tomography (2)
- photorealistic-view-synthesis (2)
- video-generation-framework (2)
- motion-patterns (2)
- image-to-3d-object-generation (2)
- patient-engagement (2)
- one-shot-learning (2)
- tibetan-script (2)
- robustness-evaluation (2)
- textual-adversarial-attack (2)
- land-use-mapping (2)
- geospatial-foundation-model (2)
- disaster-response (2)
- under-resourced-languages (2)
- security-measures (2)
- learning-bias (2)
- image-corruptions (2)
- benchmark-results (2)
- masked-autoencoders (2)
- simclr (2)
- robot-platforms (2)
- registration-accuracy (2)
- facial-representations (2)
- pixel-level-fidelity (2)
- linguistic-features (2)
- machine-generated-texts (2)
- imputation (2)
- reconstruction-based-methods (2)
- medical-reports (2)
- motion-alignment (2)
- technical-challenges (2)
- semantickitti (2)
- cross-view-consistency (2)
- multimodal-retrieval (2)
- image-embeddings (2)
- environment-dynamics (2)
- conditional-diffusion-transformer (2)
- robotic-agents (2)
- visual-priors (2)
- natural-language-interface (2)
- evolutionary-computation (2)
- question-answering-datasets (2)
- data-modalities (2)
- parallel-datasets (2)
- document-clustering (2)
- image-fidelity (2)
- long-range-interactions (2)
- safety-critical-domains (2)
- evidential-deep-learning (2)
- dense-depth-estimation (2)
- camera-motion-estimation (2)
- medical-knowledge (2)
- data-extraction (2)
- 3d-structure (2)
- dataset-combinations (2)
- mental-health (2)
- video-virtual-try-on (2)
- high-level-concepts (2)
- model-fusion (2)
- preference-optimization (2)
- multi-modal-tasks (2)
- token-importance (2)
- leaderboard (2)
- scalable-solution (2)
- image-reconstruction-task (2)
- self-supervised-training (2)
- vqvae (2)
- common-crawl (2)
- depth-images (2)
- object-masks (2)
- sinkhorn-algorithm (2)
- algorithm-design (2)
- ai-ethics (2)
- responsibility (2)
- tcn (2)
- convex-optimization (2)
- impedance-control (2)
- jet-tagging (2)
- random-matrix-theory (2)
- user-feedback (2)
- structural-health-monitoring (2)
- labeled-data (2)
- empirical-performance (2)
- domain-specific-adaptations (2)
- intrusion-detection (2)
- traffic-safety (2)
- activation (2)
- decoding (2)
- theoretical-framework (2)
- online-convex-optimization (2)
- cumulative-constraint-violation (2)
- meta-reinforcement-learning (2)
- policy-adaptation (2)
- real-time-prediction (2)
- traffic-forecasting (2)
- disentangled-embeddings (2)
- disturbances (2)
- system-throughput (2)
- distributed-inference (2)
- constrained-reinforcement-learning (2)
- navigation-tasks (2)
- closed-loop-systems (2)
- greedy-algorithm (2)
- lime (2)
- structural-analysis (2)
- coefficient-of-determination (2)
- information-fusion (2)
- convergence-speed (2)
- underfitting (2)
- extractive-question-answering (2)
- convex-loss-function (2)
- high-dimensional-inputs (2)
- safe-reinforcement-learning (2)
- nested-cross-validation (2)
- dynamic-scene-rendering (2)
- camera-viewpoint (2)
- machine-learning-as-a-service (2)
- high-dimensional-setting (2)
- sparsity-pattern (2)
- neural-systems (2)
- maximum-likelihood-estimator (2)
- stochastic-block-model (2)
- video-creation (2)
- medical-imaging-datasets (2)
- semantic-diversity (2)
- cross-modal-feature-alignment (2)
- place-recognition (2)
- domain-discrepancies (2)
- training-data-attribution (2)
- latent-feature-space (2)
- semantic-prototypes (2)
- outcome-prediction (2)
- individual-treatment-effects (2)
- deep-learning-framework (2)
- zero-knowledge-proofs (2)
- traffic-simulations (2)
- vehicle-detection (2)
- contextual-relevance (2)
- inception-score (2)
- domain-alignment (2)
- semantic-matching (2)
- computational-burden (2)
- emergent-abilities (2)
- brain-tumor-segmentation (2)
- ensemble-approach (2)
- latent-optimization (2)
- glioma-segmentation (2)
- multi-view-pedestrian-detection (2)
- signed-distance-field (2)
- mechanistic-interpretability (2)
- learning-paradigm (2)
- alignment-accuracy (2)
- multi-scale-feature-extraction (2)
- interactive-segmentation (2)
- zero-shot-segmentation (2)
- tree-like-structures (2)
- online-algorithms (2)
- reasoning-process (2)
- video-classification (2)
- quadruped-robots (2)
- safety-risks (2)
- label-skew (2)
- local-optimization (2)
- diffusion-process (2)
- physical-simulation (2)
- dynamic-3d-gaussian-splatting (2)
- identity-consistency (2)
- long-horizon-tasks (2)
- visual-coherence (2)
- large-scale-diffusion-models (2)
- viewpoint-consistency (2)
- video-frames (2)
- person-identification (2)
- training-data-generation (2)
- resource-usage (2)
- procedural-knowledge (2)
- document-classification (2)
- multi-objective-learning (2)
- architectural-design (2)
- framing-effect (2)
- cognitive-biases (2)
- image-feature-extraction (2)
- text-representation (2)
- clip-representations (2)
- automated-program-repair (2)
- ray-sampling (2)
- cifar-10-dataset (2)
- mnist-dataset (2)
- frechet-inception-distance (2)
- q-learning (2)
- language-capabilities (2)
- generalist-models (2)
- language-tasks (2)
- supervised-baselines (2)
- 2d-features (2)
- 6d-object-pose-estimation (2)
- image-manipulations (2)
- novel-view-rendering (2)
- image-localization (2)
- localized-image-editing (2)
- gpt-4v (2)
- self-occlusions (2)
- geometric-constraints (2)
- natural-language-tasks (2)
- relevance (2)
- psychological-counseling (2)
- feature-learning (2)
- model-prediction (2)
- multimodal-generative-model (2)
- sewing-patterns (2)
- dutch-language (2)
- symbolic-music-generation (2)
- dataset-imbalance (2)
- detr (2)
- command-line-interfaces (2)
- cross-modal-task (2)
- image-classification-datasets (2)
- efficiency-and-performance (2)
- inpainting-technique (2)
- bleu-scores (2)
- frontier-models (2)
- global-model-accuracy (2)
- communication-constraints (2)
- performance-based-ranking (2)
- video-interpolation (2)
- conditional-generation-tasks (2)
- frame-prediction (2)
- spatial-resolution (2)
- zero-shot-prompting (2)
- static-scenes (2)
- identity-verification (2)
- self-distillation (2)
- response-generation (2)
- verification (2)
- robot-experiments (2)
- point-based-methods (2)
- predictive-language-models (2)
- integrated-gradients (2)
- multiple-choice-qa (2)
- open-weight-models (2)
- open-source-datasets (2)
- directed-acyclic-graphs (2)
- gan-framework (2)
- tracking-problem (2)
- computing-power (2)
- geometric-accuracy (2)
- proper-orthogonal-decomposition (2)
- systematic-study (2)
- koopman-autoencoders (2)
- short-term-memory (2)
- latent-confounders (2)
- disentangled-representation-learning (2)
- unstructured-environments (2)
- hierarchical-architecture (2)
- ai-driven-framework (2)
- aiops (2)
- data-errors (2)
- societal-biases (2)
- transformer-based-large-language-models (2)
- layer-normalization (2)
- renewable-energy-integration (2)
- data-centers (2)
- privacy-preserving-machine-learning (2)
- disparate-impact (2)
- radial-basis-functions (2)
- bayesian-optimisation (2)
- magnetic-resonance-images (2)
- post-processing (2)
- learning-algorithms (2)
- group-fairness (2)
- demographic-parity (2)
- domain-specific-languages (2)
- cognitive-architecture (2)
- learning-objectives (2)
- maze-navigation (2)
- multi-step-prediction (2)
- literature-review (2)
- sparse-measurements (2)
- high-dimensional-problems (2)
- feature-disentanglement (2)
- model-scalability (2)
- high-quality-generation (2)
- quality-assessment (2)
- large-multimodality-models (2)
- symmetries (2)
- image-quality-metrics (2)
- planning-capabilities (2)
- deepfakes (2)
- standardized-datasets (2)
- meta-analysis (2)
- clinical-importance (2)
- convolutional-autoencoders (2)
- data-embedding (2)
- inter-class-confusion (2)
- tiny-imagenet (2)
- end-to-end-framework (2)
- high-resolution-multispectral-images (2)
- medical-data-analysis (2)
- neural-network-analysis (2)
- clinical-relevance (2)
- gradient-backpropagation (2)
- active-speaker-detection (2)
- image-generation-models (2)
- shortcut-learning (2)
- mitigation (2)
- transformer-based-diffusion-model (2)
- attention-based-mechanism (2)
- cross-attention-maps (2)
- re-identification (2)
- zero-shot-accuracy (2)
- occluded-regions (2)
- distribution-matching (2)
- software-vulnerabilities (2)
- vulnerability-assessment (2)
- streaming-inference (2)
- digital-platforms (2)
- hybrid-representations (2)
- data-protection (2)
- multimodal-content (2)
- surface-reconstruction (2)
- multi-image-understanding (2)
- 3d-motion-models (2)
- wearable-sensors (2)
- generative-network (2)
- literary-analysis (2)
- algorithmic-fairness (2)
- mimic-cxr-dataset (2)
- radiology-report-generation (2)
- data-composition (2)
- gated-recurrent-units (2)
- classical-planning (2)
- agency (2)
- marginalized-communities (2)
- audio-features (2)
- large-audio-language-models (2)
- multimodal-ai (2)
- open-access-dataset (2)
- automated-model-selection (2)
- imagenet-1k (2)
- clinical-scenarios (2)
- preference-data (2)
- text-corpora (2)
- language-model-training (2)
- grounding (2)
- unfairness (2)
- adaptive-learning-rate (2)
- control-techniques (2)
- inverse-dynamics (2)
- benchmarking-methods (2)
- granular-ball-computing (2)
- voice-input (2)
- aggregation (2)
- compatibility (2)
- model-counting (2)
- robotic-perception (2)
- spatial-geometry (2)
- 3d-scenes (2)
- mapping-framework (2)
- combinatorial-explosion (2)
- communication-systems (2)
- remote-health-monitoring (2)
- real-life-applications (2)
- time-series-foundation-model (2)
- sampling-based-motion-planning (2)
- privacy-attacks (2)
- openstreetmap (2)
- security-vulnerabilities (2)
- online-education (2)
- learning-analytics (2)
- minimally-invasive-surgery (2)
- trust-in-ai (2)
- performance-assessment (2)
- computational-power (2)
- theoretical-explanation (2)
- asymmetric-learning (2)
- treatment-outcomes (2)
- data-size (2)
- control-methods (2)
- expressivity (2)
- planning-problems (2)
- automated-planning (2)
- nonlinear-function (2)
- model-based-reinforcement-learning (2)
- parameter-identification (2)
- inductive-biases (2)
- sparse-subnetworks (2)
- iterative-magnitude-pruning (2)
- topological-properties (2)
- inertial-navigation (2)
- kalman-filter (2)
- non-stationary-environments (2)
- gating-mechanism (2)
- fourier-neural-operators (2)
- differentiable-simulation (2)
- action-space (2)
- graph-data (2)
- grad-cam (2)
- text-to-3d (2)
- image-to-3d (2)
- parameter-efficient-adaptation (2)
- diagnostic-models (2)
- long-term-predictions (2)
- seasonal-trend-decomposition (2)
- memory-retrieval (2)
- graph-based-approach (2)
- standardized-evaluation (2)
- multi-head-attention (2)
- unsupervised-anomaly-detection (2)
- functional-magnetic-resonance-imaging (2)
- mixed-precision-quantization (2)
- system-heterogeneity (2)
- turing-test (2)
- image-augmentations (2)
- high-fidelity-images (2)
- image-text-paired-data (2)
- progressive-training-strategy (2)
- gaussian-functions (2)
- isolation-forest (2)
- engineering-design (2)
- parallel-generation (2)
- node-features (2)
- skeleton (2)
- dynamic-range (2)
- sparse-view-reconstruction (2)
- pixel-level-annotations (2)
- consistency-distillation (2)
- flow-matching-models (2)
- object-hallucinations (2)
- semantic-modeling (2)
- cognitive-science (2)
- feedback-loop (2)
- no-reference-image-quality-assessment (2)
- image-preprocessing (2)
- constructive-feedback (2)
- fundus-images (2)
- multimodal-training (2)
- high-fidelity-generation (2)
- multimodal-understanding (2)
- openvla (2)
- radiotherapy (2)
- generative-methods (2)
- diffusion (2)
- sequence-prediction (2)
- joint-distribution (2)
- multi-armed-bandit-algorithm (2)
- dynamic-reward-function (2)
- binary-search (2)
- custom-dataset (2)
- aerial-imagery (2)
- classification-techniques (2)
- data-manifold (2)
- denoising-network (2)
- colorization (2)
- degradation-factors (2)
- real-time-scenarios (2)
- geospatial-data (2)
- vector-representations (2)
- textual-prompts (2)
- segment-anything-model-sam (2)
- detector-performance (2)
- masking-strategy (2)
- large-pretrained-models (2)
- model-size-reduction (2)
- inference-framework (2)
- non-verbal-interactions (2)
- numerical-weather-prediction (2)
- precision-and-recall (2)
- doppelgangers (2)
- concept-erasure (2)
- linear-algebra (2)
- prior-preservation (2)
- online-platforms (2)
- attack-performance (2)
- quality-of-experience (2)
- large-scale-benchmark (2)
- multimodal-approaches (2)
- baseline-models (2)
- memory-constrained-environments (2)
- memory-savings (2)
- inference-stage (2)
- image-representations (2)
- retrieval-systems (2)
- hallucination-mitigation (2)
- model-convergence (2)
- success-rate (2)
- causal-language-modeling (2)
- masked-language-modeling (2)
- indoor-datasets (2)
- relocalization (2)
- sequential-information (2)
- cross-dataset-generalization (2)
- global-context (2)
- associative-memories (2)
- process-reward-models (2)
- modular-architecture (2)
- inference-time-strategies (2)
- sentence-embeddings (2)
- parameter-efficient-models (2)
- calibration-method (2)
- objective-function (2)
- 2d-diffusion-models (2)
- denoising-diffusion (2)
- 3d-optimization (2)
- robot-policies (2)
- state-representation (2)
- linguistic-knowledge (2)
- non-verbal-communication (2)
- multi-view-learning (2)
- tool-learning (2)
- supervised-machine-learning (2)
- confidence-intervals (2)
- simulation-based-inference (2)
- efficientnetv2 (2)
- encoder-only-models (2)
- inter-annotator-agreement (2)
- composed-image-retrieval (2)
- robotic-arms (2)
- kinematic-analysis (2)
- object-relations (2)
- data-construction-pipeline (2)
- depth-information (2)
- experimental-dataset (2)
- event-streams (2)
- temporal-contexts (2)
- gaussian-splats (2)
- breast-cancer (2)
- specificity (2)
- reward-hacking (2)
- mbpp (2)
- automated-code-generation (2)
- humaneval (2)
- llm-evaluation (2)
- question-answering-performance (2)
- informativeness (2)
- 3d-dense-captioning (2)
- 3d-visual-grounding (2)
- large-datasets (2)
- redundant-information (2)
- digitalization (2)
- fine-grained-recognition (2)
- temporal-relationships (2)
- historical-data (2)
- character-consistency (2)
- sequence-modeling (2)
- decoupled-cross-attention-mechanisms (2)
- video-diffusion-prior (2)
- unreal-engine (2)
- texture-generation (2)
- report-generation (2)
- multimodal-evaluations (2)
- real-world-objects (2)
- causal-transformer (2)
- error-accumulation (2)
- regulatory-approaches (2)
- patient-subgroups (2)
- physicochemical-properties (2)
- parameter-inference (2)
- in-vitro-experiments (2)
- cluttered-environments (2)
- optical-flow-estimation (2)
- cross-modal-data (2)
- real-time-analysis (2)
- time-series-classification (2)
- model-explanations (2)
- personality-traits (2)
- molecular-design (2)
- bleu (2)
- ai-alignment (2)
- negative-feedback (2)
- utility (2)
- network-throughput (2)
- load-balancing (2)
- visualisation (2)
- readability (2)
- complex-reasoning (2)
- neural-differential-equations (2)
- interactive-systems (2)
- model-alignment (2)
- neural-operator-architecture (2)
- artifacts (2)
- equivariant-neural-networks (2)
- user-embedding (2)
- labeled-dataset (2)
- fully-supervised-approaches (2)
- dexterous-manipulation (2)
- symbolic-regression (2)
- deep-convolutional-neural-networks (2)
- structured-sparsity (2)
- latency-reduction (2)
- dynamic-compression (2)
- model-utility (2)
- prompt-injection-attacks (2)
- clinical-data (2)
- logistics (2)
- temporal-stability (2)
- face-swapping (2)
- scaling-behavior (2)
- coding-tasks (2)
- extrapolation (2)
- multi-image-inputs (2)
- distributed-machine-learning (2)
- collaborative-training (2)
- multimodal-entity-linking (2)
- speaker-diarization (2)
- personalized-recommendations (2)
- news-articles (2)
- politics (2)
- climate-modeling (2)
- python-code-generation (2)
- trade-offs (2)
- dynamic-reconfiguration (2)
- machine-intelligence (2)
- ai-advancements (2)
- toxic-prompts (2)
- zero-shot-evaluation (2)
- opinion-mining (2)
- copyright (2)
- qa-datasets (2)
- pretrained-diffusion-models (2)
- older-adults (2)
- locomotion (2)
- k-12-education (2)
- perceptron-algorithm (2)
- clean-energy (2)
- medicine (2)
- environmental-protection (2)
- out-of-distribution (2)
- instruction-data (2)
- data-generation-process (2)
- visual-genome (2)
- multimodal-question-answering (2)
- innovation (2)
- personalized-medicine (2)
- global-representation (2)
- dynamic-learning-rates (2)
- video-action-detection (2)
- fashion-design (2)
- text-summarization (2)
- preprocessing (2)
- multimodal-classification (2)
- flow-field (2)
- risk-stratification (2)
- multi-omics-data (2)
- bounding-boxes (2)
- korean-culture (2)
- uncertainty-assessments (2)
- greedy-decoding (2)
- open-source-framework (2)
- universal-adversarial-perturbations (2)
- semantickitti-dataset (2)
- numerical-experimentation (2)
- fairness-issues (2)
- facial-analysis (2)
- evaluation-criteria (2)
- sequential-problems (2)
- symbolic-reasoning (2)
- propositional-logic (2)
- landing-maneuver (2)
- clip-models (2)
- autoregressive-transformer-models (2)
- neuromorphic-hardware (2)
- data-incompleteness (2)
- image-rendering (2)
- high-quality-meshes (2)
- geometry-optimization (2)
- photometric-stereo (2)
- image-generator (2)
- story-visualization (2)
- robust-feature-representations (2)
- temporal-networks (2)
- ensemble-framework (2)
- elderly-care (2)
- geometric-deep-learning (2)
- dynamic-graph-embedding (2)
- audio-visual-correlation (2)
- graph-edit-distance (2)
- distributional-semantics (2)
- language-processing (2)
- similarity (2)
- factor-graph (2)
- robotic-operating-system (2)
- collision-free-trajectories (2)
- linguistic-patterns (2)
- natural-language (2)
- multi-resolution-training (2)
- multi-teacher-distillation (2)
- simulation-testing (2)
- gdpr (2)
- anonymization (2)
- prediction (2)
- semantic-guidance (2)
- semantic-space (2)
- context-based-approaches (2)
- model-comparison (2)
- autoregressive-modeling (2)
- image-to-video-generation (2)
- local-object-motion (2)
- social-bias (2)
- multi-view-generation (2)
- frame-interpolation (2)
- self-supervised-contrastive-learning (2)
- accuracy-evaluation (2)
- style-extraction (2)
- social-robot-navigation (2)
- transformer-based-llm (2)
- long-tail-distributions (2)
- infinitesimal-generator (2)
- spectral-properties (2)
- text-annotation (2)
- hierarchical-reinforcement-learning (2)
- non-stationarity (2)
- decision-boundaries (2)
- model-scale (2)
- automated-decision-making (2)
- motion-primitives (2)
- llm-powered-agents (2)
- llm-safety (2)
- high-resolution (2)
- data-pruning (2)
- planning-tasks (2)
- variational-lower-bound (2)
- split-federated-learning (2)
- model-aggregation (2)
- geometric-transformations (2)
- presentation-attacks (2)
- cognitive-processes (2)
- bioinformatics (2)
- local-sgd (2)
- research-efficiency (2)
- end-to-end-systems (2)
- data-visualization (2)
- sql (2)
- fine-grained-perception (2)
- 3d-perception (2)
- sparsification (2)
- streaming-datasets (2)
- hierarchical-model (2)
- score-based-generative-models (2)
- score-functions (2)
- parameter-efficient-tuning (2)
- sim-to-real-transfer (2)
- normalizing-flow-models (2)
- partially-observable-markov-decision-processes (2)
- feature-reconstruction (2)
- stable-video-diffusion (2)
- keyframes (2)
- image-translation (2)
- character-customization (2)
- scene-reconstruction (2)
- binary-segmentation (2)
- tables (2)
- kernel-regression (2)
- remote-sensing-imagery (2)
- quality-control (2)
- reading-comprehension-datasets (2)
- model-quality (2)
- mixed-method-approach (2)
- biosignals (2)
- multi-step-tasks (2)
- ai-assistants (2)
- web-interfaces (2)
- implicit-bias (2)
- velocity-field (2)
- training-schedule (2)
- neural-language-models (2)
- natural-language-representations (2)
- integrated-development-environments (2)
- evolutionary-strategies (2)
- expectation-maximization-algorithm (2)
- bias-correction (2)
- empirical-evidence (2)
- imu (2)
- software-systems (2)
- fuzz-testing (2)
- conditional-image-generation (2)
- syntactic-structure (2)
- montreal-forced-aligner (2)
- raman-spectroscopy (2)
- vehicle-safety (2)
- multi-modal-feature-fusion (2)
- entity-recognition (2)
- treatment-planning (2)
- open-source-toolbox (2)
- dynamic-time-warping (2)
- probabilistic-circuits (2)
- centralized-training (2)
- cross-domain-evaluations (2)
- convex-functions (2)
- age-estimation (2)
- resource-constrained-hardware (2)
- safety-filters (2)
- human-preference-alignment (2)
- dall-e (2)
- hierarchical-classification (2)
- visible-infrared-person-re-identification (2)
- data-processing-pipelines (2)
- misalignment-issues (2)
- 3d-semantic-occupancy-prediction (2)
- zero-shot-reasoning (2)
- model-based-planning (2)
- answer-accuracy (2)
- long-context (2)
- point-cloud-completion (2)
- multimodal-framework (2)
- prompt-selection (2)
- feed-forward-neural-network (2)
- hyperedges (2)
- data-science (2)
- batched-inference (2)
- spatial-consistency (2)
- geometric-priors (2)
- false-negatives (2)
- failure-modes (2)
- real-world-deployment (2)
- model-adaptation (2)
- online-reinforcement-learning (2)
- agent-framework (2)
- synthetic-data-augmentation (2)
- traffic-flow-prediction (2)
- restless-multi-armed-bandits (2)
- contextual-coherence (2)
- semantic-accuracy (2)
- robotic-hands (2)
- text-features (2)
- r2-score (2)
- real-time-clinical-use (2)
- 3d-objects (2)
- texture-refinement (2)
- mesh-generation (2)
- similarity-scores (2)
- animation (2)
- soft-prompt (2)
- topic-classification (2)
- question-answering-tasks (2)
- amino-acid-sequences (2)
- helpfulness (2)
- appearance-transfer (2)
- neural-network-representations (2)
- geospatial-artificial-intelligence (2)
- single-task-learning (2)
- synthetic-samples (2)
- electrical-impedance-tomography (2)
- universal-approximation-theorem (2)
- temporal-fusion (2)
- llm-agent (2)
- automated-grading (2)
- facial-identity (2)
- environmental-perception (2)
- randomized-controlled-experiment (2)
- llm-training (2)
- pca (2)
- umap (2)
- gpt-2-xl (2)
- knowledge-tracing (2)
- contextualized-embeddings (2)
- drones (2)
- malware-classification (2)
- generator (2)
- retrieval-accuracy (2)
- control-policy (2)
- adaptive-control (2)
- illumination-effects (2)
- dialogue-systems (2)
- trusted-execution-environments (2)
- collaborative-learning (2)
- quadratic-complexity (2)
- multiagent-path-finding (2)
- parameterized-complexity (2)
- first-order-logic (2)
- adapter-based-methods (2)
- fine-grained-features (2)
- question-answering-systems (2)
- eeg (2)
- physical-neural-networks (2)
- channel-attention (2)
- scene-editing (2)
- person-re-identification (2)
- gait (2)
- 3d-skeleton-data (2)
- auxiliary-tasks (2)
- industrial-dataset (2)
- intent-classifier (2)
- matryoshka-representation-learning (2)
- math-reasoning (2)
- sentence-representation (2)
- gradient-estimators (2)
- nonlinear-programming (2)
- structural-entropy (2)
- trajectory-estimation (2)
- code-correctness (2)
- image-text-matching (2)
- synthesis-quality (2)
- reasoning-instructions (2)
- performance-gap (2)
- constrained-markov-decision-processes (2)
- cumulative-rewards (2)
- temporal-features (2)
- joint-training (2)
- semantic-fidelity (2)
- generative-paradigms (2)
- refinement (2)
- temporal-action-localization (2)
- visual-odometry (2)
- social-determinants-of-health (2)
- open-set-object-detection (2)
- uplift-modeling (2)
- causal-machine-learning (2)
- prompt-augmentation (2)
- debiasing (2)
- cross-lingual-evaluation (2)
- 3d-human-avatars (2)
- virtual-environments (2)
- entropy (2)
- scene-level-reconstruction (2)
- camera-parameter-estimation (2)
- echo-chamber (2)
- covid-19-pandemic (2)
- search-space-reduction (2)
- visual-tasks (2)
- 2d-diffusion-priors (2)
- human-visual-system (2)
- data-synthesis-pipeline (2)
- state-of-the-art (2)
- volumetric-video (2)
- mixture-model (2)
- intervention (2)
- task-specific-performance (2)
- reasoning-capacities (2)
- nlp-datasets (2)
- process-supervision (2)
- problem-solving-abilities (2)
- rotary-position-embedding (2)
- attention-patterns (2)
- long-context-llms (2)
- theory-of-mind (2)
- hierarchical-planning (2)
- syntactic-features (2)
- tracking-performance (2)
- python-package (2)
- virtual-screening (2)
- offline-training (2)
- dynamic-conditions (2)
- identity-information (2)
- word-sense-disambiguation (2)
- interpretable-machine-learning (2)
- mild-cognitive-impairment (2)
- drug-development (2)
- luxembourgish (2)
- intraclass-correlation-coefficient (2)
- experimental-study (2)
- message-passing-neural-networks (2)
- political-debate (2)
- training-model (2)
- multi-agent-environments (2)
- input-modalities (2)
- performance-measurements (2)
- temporal-data (2)
- visual-comprehension (2)
- discriminative-models (2)
- non-convex-optimization (2)
- sparse-optimization (2)
- deep-q-networks (2)
- mixing-times (2)
- power-conversion-efficiency (2)
- decentralized-systems (2)
- split-learning (2)
- data-security (2)
- nonconvex-objectives (2)
- exploration (2)
- link-sign-prediction (2)
- signed-graph-neural-networks (2)
- graph-theory (2)
- fire-dynamics (2)
- gpt-model (2)
- manifold-learning (2)
- mean-embeddings (2)
- deep-deterministic-policy-gradient (2)
- gps-denied-environment (2)
- preference-datasets (2)
- pruning-strategies (2)
- online-communities (2)
- interpretable-ai-systems (2)
- semantic-parsing (2)
- quantum-kernel-methods (2)
- statistical-inference (2)
- python-library (2)
- conditional-distribution (2)
- mobile-computing (2)
- quantum-algorithms (2)
- undirected-graphs (2)
- automated-analysis (2)
- first-order-methods (2)
- design-generation (2)
- reward-mechanism (2)
- language-generation (2)
- ai-methods (2)
- research-opportunities (2)
- fully-homomorphic-encryption (2)
- vision-transformer-architectures (2)
- transformer-based-framework (2)
- view-dependent-appearance (2)
- structured-representation (2)
- gradient-information (2)
- kolmogorov-complexity (2)
- parameter-efficient-methods (2)
- pairwise-comparisons (2)
- causal-consistency (2)
- generalist-policies (2)
- financial-sentiment-analysis (2)
- combinatorial-optimization-problems (2)
- model-compactness (2)
- teacher-model (2)
- student-model (2)
- vqa (2)
- mujoco-environment (2)
- patch-selection (2)
- state-of-the-art-algorithms (2)
- residual-connections (2)
- image-forgery-localization (2)
- ai-risks (2)
- civil-society (2)
- safety-assurances (2)
- translation-quality (2)
- visual-cue (2)
- semantic-context (2)
- relevance-scores (2)
- speech-emotion-recognition (2)
- cross-modal-interactions (2)
- gpu-memory (2)
- language-families (2)
- segmentation-tasks (2)
- accuracy-loss (2)
- discrimination (2)
- social-norms (2)
- lexical-diversity (2)
- diffusion-based-framework (2)
- medical-practice (2)
- misclassification-costs (2)
- performance-measures (2)
- mask-generator (2)
- inter-object-relationships (2)
- chart-understanding (2)
- table-understanding (2)
- cooperative-perception (2)
- kubernetes (2)
- resource-constrained-scenarios (2)
- grammar-errors (2)
- granularity-levels (2)
- factuality (2)
- edge-applications (2)
- language-adaptation (2)
- cross-lingual-alignment (2)
- domain-knowledge (2)
- lstm-based-models (2)
- gaze-tracking (2)
- search-space-pruning (2)
- spatial-temporal-dynamics (2)
- safety-verification (2)
- open-source-library (2)
- apollo (2)
- training-acceleration (2)
- low-rank-adapters (2)
- 3d-occupancy-prediction (2)
- systematic-evaluation (2)
- transformer-based-generative-model (2)
- computer-aided-drug-discovery (2)
- model-collapse (2)
- lip-synchronization (2)
- spatiotemporal-dynamics (2)
- fairlearn (2)
- fairness-libraries (2)
- aif360 (2)
- ml-workflows (2)
- linear-temporal-logic (2)
- graphs (2)
- conditional-mutual-information (2)
- ppo-algorithm (2)
- design-space (2)
- model-validation (2)
- monitoring (2)
- data-sources (2)
- question-generation (2)
- text-segmentation (2)
- skeleton-based-action-recognition (2)
- multi-view-cameras (2)
- appearance-features (2)
- user-privacy (2)
- variance-reduction (2)
- magnitude-pruning (2)
- bengali-language (2)
- missing-data (2)
- simulation-benchmark (2)
- inference-speedup (2)
- degraded-images (2)
- distance-measures (2)
- accuracy-enhancement (2)
- materials-science (2)
- physical-properties (2)
- biological-concepts (2)
- lpips (2)
- cognitive-modeling (2)
- object-goal-navigation (2)
- mobile-manipulation (2)
- prior-knowledge (2)
- mental-health-assessment (2)
- policymaking (2)
- mask-reconstruction (2)
- balanced-accuracy (2)
- multi-modal-inputs (2)
- quality (2)
- astronomy (2)
- depth-camera (2)
- audio-domain (2)
- llm-performance (2)
- robust-principal-component-analysis (2)
- reasoning-skills (2)
- discriminative-features (2)
- 3d-data (2)
- temporal-patterns (2)
- radar-camera-fusion (2)
- rgb-videos (2)
- self-verification (2)
- product-recommendations (2)
- noise-scheduling (2)
- sota-performance (2)
- low-cost-sensors (2)
- query-rewriting (2)
- individual-differences (2)
- fingerprint-recognition (2)
- multilingual-pretrained-language-models (2)
- gait-analysis (2)
- reality-gap (2)
- privacy-preserving (2)
- prototype-learning (2)
- metric-depth-estimation (2)
- implicit-differentiation (2)
- privacy-constraints (2)
- financial-datasets (2)
- transformer-neural-networks (2)
- temporal-localization (2)
- big-five-personality-traits (2)
- gpt-4-turbo (2)
- robotic-grasping (2)
- real-time-adaptation (2)
- wearable-devices (2)
- task-allocation (2)
- robotic-applications (2)
- joint-embedding-predictive-architecture (2)
- diffusion-probabilistic-models (2)
- continuous-learning (2)
- code-reliability (2)
- language-documentation (2)
- semantics (2)
- data-transmission (2)
- decoder-only-models (2)
- modality-alignment (2)
- modal-imbalance (2)
- entropy-maximization (2)
- environmental-interactions (2)
- species-classification (2)
- entropy-regularization (2)
- empirical-experiments (2)
- math-benchmark (2)
- receptive-fields (2)
- rgb-d-images (2)
- safety-challenges (2)
- machine-learning-predictions (2)
- visual-captioning (2)
- human-intents (2)
- offline-dataset (2)
- evaluation-models (2)
- out-of-domain-tasks (2)
- nonlinear-inverse-problems (2)
- feedback-signals (2)
- patch-deformation (2)
- deformation-instability (2)
- avatar-generation (2)
- mapper-algorithm (2)
- semantic-cues (2)
- environmental-monitoring (2)
- confidence-score (2)
- pruning-techniques (2)
- lightweight-network-design (2)
- metadata (2)
- parametric-knowledge (2)
- instruction-tuned-large-language-models (2)
- environment-maps (2)
- functional-properties (2)
- interior-point-methods (2)
- coherence (2)
- time-efficiency (2)
- data-free-knowledge-distillation (2)
- knowledge-graph-reasoning (2)
- sparse-rewards (2)
- 3d-human-pose-estimation (2)
- graph-unlearning (2)
- multilingual-llms (2)
- multi-task-reinforcement-learning (2)
- defense-methods (2)
- continuous-control-tasks (2)
- semantic-properties (2)
- image-caption-pairs (2)
- mathematical-problems (2)
- open-domain-qa-datasets (2)
- structured-outputs (2)
- peer-review (2)
- open-source-projects (2)
- simulation-training (2)
- spectral-graph-neural-networks (2)
- numerical-calculations (2)
- bundle-adjustment (2)
- quadrotor-control (2)
- visual-effects (2)
- quality-improvement (2)
- information-processing (2)
- biological-systems (2)
- computational-graph (2)
- feature-extraction-methods (2)
- fidelity (2)
- authenticity (2)
- cross-view-geo-localization (2)
- wildfire-monitoring (2)
- burned-area-mapping (2)
- retrieval-models (2)
- information-gain (2)
- cardiovascular-disease (2)
- energy-conservation (2)
- simulation-data (2)
- blur-kernel-estimation (2)
- np-hard-problems (2)
- ade20k-dataset (2)
- class-incremental-learning (2)
- partial-observation (2)
- kernel-ridge-regression (2)
- spatio-temporal-forecasting (2)
- vector-embedding (2)
- fact-verification (2)
- ai-literacy (2)
- security-risks (2)
- multi-scale-feature-fusion (2)
- dataset-curation (2)
- graph-reasoning (2)
- clinical-settings (2)
- attention-modules (2)
- regression-models (2)
- learning (2)
- long-term-time-series-forecasting (2)
- performance-bottleneck (2)
- tool-augmented-llms (2)
- knowledge-editing (2)
- thought-generation (2)
- pipeline-construction (2)
- traffic-simulator (2)
- evaluation-suite (2)
- machine-generated-content (2)
- temporal-relations (2)
- recommendation-algorithms (2)
- embedding-quality (2)
- low-resource-contexts (2)
- optimal-policies (2)
- value-based-algorithms (2)
- visual-information (2)
- multi-hop-qa (2)
- machine-learning-training (2)
- reinforcement-learning-algorithms (2)
- uci-machine-learning-repository (2)
- edge-detection (2)
- utility-preservation (2)
- human-like-reasoning (2)
- chemical-composition (2)
- rag (2)
- agents (2)
- photometric-error (2)
- self-supervised-framework (2)
- text-to-image (2)
- model-capacity (2)
- long-short-term-memory-lstm (2)
- expressive-power (2)
- weakly-supervised-semantic-segmentation (2)
- interpretable-policies (2)
- np-completeness (2)
- finite-scalar-quantization (2)
- two-stage-training-process (2)
- whole-body-control (2)
- data-obfuscation (2)
- eye-tracking (2)
- hierarchical-clustering (2)
- sequence-length (2)
- inductive-reasoning (2)
- rule-learning (2)
- power-grids (2)
- binary-classifier (2)
- computational-photography (2)
- communication (2)
- hypothesis-generation (2)
- model-outputs (2)
- active-inference (2)
- hierarchical-relationships (2)
- roc-curve (2)
- model-selection (2)
- uncertainty-calibration (2)
- physiological-signals (2)
- long-tailed-distribution (2)
- spectral-clustering (2)
- similarity-measure (2)
- transformer-module (2)
- hash-encodings (2)
- code-summarization (2)
- multi-party-dialogues (2)
- cognitive-maps (2)
- time-of-flight-cameras (2)
- rgb-cameras (2)
- dpo (2)
- glider (2)
- generalization-issues (2)
- fluid-dynamics (2)
- masked-auto-encoding (2)
- photorealistic-novel-view-synthesis (2)
- maximum-likelihood-estimation (2)
- wearable-robotics (2)
- image-to-3d-generation (2)
- longbench (2)
- interactive-environments (2)
- microrobots (2)
- hallucination-detection (2)
- Published on
Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation
3D-geometric-informationimplicit-and-explicit-3D-representationsself-supervised-fine-tuningspatial-relationshipsspatial-geometry2D-foundation-modelspoint-cloud-datalarge-scale-pretrained-knowledgesimulation-benchmarksrobotic-manipulationtask-aware-masked-autoencoderLift3D-frameworkpositional-mappingreal-world-scenarios3D-features-extractionlarge-scale-robotic-3D-data• State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University• Beijing Academy of Artificial Intelligence (BAAI)• CUHK- Published on
• Beijing University of Posts and Telecommunications- Published on
- Published on
• Key Laboratory of Water Big Data Technology of Ministry of Water Resources, Hohai University, 211100 Nanjing, China.- Published on
- Published on
• Tsinghua University• University of California, Berkeley- Published on
- Published on
A Riemannian Take on Distance Fields and Geodesic Flows in Robotics
non-Euclidean-structuresRiemannian-eikonal-equationgeodesicshigh-dimensional-spacesRiemannian-metricminimal-energy-trajectorieslearning-techniquesgeodesic-distance-fieldpartial-differential-equationenergy-aware-motion-generationdistance-functionsoptimization-techniquesroboticsspatial-relationshipscontrol-techniquesgradient-flowphysics-informed-neural-networks• Sunrise Setting Ltd, UK• SAGE Publications Ltd, UK- Published on