- Published on
• School of Computer Science and Technology, East China Normal University• Utrecht University, the Netherlands• Midea Group
Research
Select a Tag
- large-language-models (470)
- reinforcement-learning (117)
- machine-learning (78)
- deep-learning (73)
- vision-language-models (57)
- benchmarking (56)
- computational-efficiency (54)
- neural-networks (48)
- diffusion-models (46)
- robustness (41)
- language-models (41)
- multimodal-large-language-models (40)
- artificial-intelligence (39)
- fine-tuning (38)
- generative-models (35)
- retrieval-augmented-generation (34)
- interpretability (34)
- generalization (33)
- dataset (29)
- benchmark (29)
- federated-learning (27)
- model-performance (27)
- natural-language-processing (27)
- graph-neural-networks (25)
- benchmark-datasets (24)
- scalability (24)
- deep-neural-networks (23)
- feature-extraction (23)
- self-supervised-learning (23)
- convolutional-neural-networks (22)
- evaluation-metrics (22)
- computer-vision (22)
- in-context-learning (21)
- evaluation-framework (21)
- data-augmentation (21)
- transformers (21)
- computational-cost (21)
- supervised-fine-tuning (20)
- contrastive-learning (20)
- latent-space (19)
- hallucinations (19)
- accuracy (18)
- foundation-models (18)
- direct-preference-optimization (18)
- performance-improvement (18)
- few-shot-learning (18)
- efficiency (17)
- image-generation (17)
- computational-complexity (16)
- numerical-experiments (16)
- llms (16)
- healthcare (15)
- multi-agent-systems (15)
- vision-transformers (15)
- performance-evaluation (15)
- image-classification (14)
- knowledge-graphs (14)
- computational-overhead (14)
- knowledge-transfer (14)
- deep-learning-models (14)
- downstream-tasks (14)
- autonomous-driving (14)
- adversarial-attacks (14)
- classification (14)
- 3d-gaussian-splatting (14)
- chain-of-thought-reasoning (14)
- low-resource-languages (14)
- deep-reinforcement-learning (14)
- text-to-image-generation (14)
- sample-efficiency (14)
- decision-making (13)
- empirical-evaluations (13)
- state-of-the-art-performance (13)
- transfer-learning (13)
- overfitting (13)
- prompt-engineering (13)
- knowledge-distillation (13)
- machine-translation (13)
- uncertainty-quantification (13)
- synthetic-dataset (13)
- large-vision-language-models (13)
- theoretical-analysis (12)
- parameter-efficient-fine-tuning (12)
- reasoning-capabilities (12)
- evaluation-benchmarks (12)
- mathematical-reasoning (12)
- generative-ai (12)
- data-scarcity (12)
- attention-mechanisms (12)
- catastrophic-forgetting (12)
- transformer-based-models (11)
- code-generation (11)
- reasoning (11)
- supervised-learning (11)
- f1-score (11)
- text-generation (11)
- automatic-speech-recognition (11)
- medical-imaging (11)
- zero-shot-learning (11)
- quantization (10)
- video-understanding (10)
- generative-modeling (10)
- multi-agent-reinforcement-learning (10)
- benchmark-evaluation (10)
- multi-task-learning (10)
- privacy-concerns (10)
- fairness (10)
- low-rank-adaptation (10)
- visual-question-answering (10)
- unsupervised-learning (10)
- large-scale-dataset (10)
- differential-privacy (10)
- object-detection (10)
- robotics (10)
- explainability (10)
- classification-accuracy (9)
- curriculum-learning (9)
- reward-functions (9)
- generalization-capabilities (9)
- synthetic-data (9)
- regret-bounds (9)
- variational-autoencoders (9)
- model-generalization (9)
- model-robustness (9)
- real-world-datasets (9)
- multiple-choice-questions (9)
- preference-optimization (9)
- edge-computing (9)
- alzheimers-disease (8)
- pre-trained-language-models (8)
- explainable-ai (8)
- group-relative-policy-optimization (8)
- policy-optimization (8)
- distribution-shifts (8)
- semantic-understanding (8)
- clip (8)
- time-series-forecasting (8)
- node-classification (8)
- dynamic-environments (8)
- instruction-tuning (8)
- convergence-rate (8)
- data-privacy (8)
- information-retrieval (8)
- question-answering (8)
- data-heterogeneity (8)
- machine-unlearning (8)
- computational-resources (8)
- class-imbalance (8)
- continual-learning (8)
- bert (8)
- education (8)
- trustworthiness (8)
- world-models (8)
- reasoning-tasks (7)
- performance-degradation (7)
- cnns (7)
- transparency (7)
- chain-of-thought-prompting (7)
- theoretical-framework (7)
- model-training (7)
- robotic-manipulation (7)
- optimization (7)
- trajectory-planning (7)
- sentiment-analysis (7)
- image-datasets (7)
- pre-training (7)
- machine-learning-models (7)
- proximal-policy-optimization (7)
- model-architectures (7)
- social-media (7)
- feature-learning (7)
- stochastic-gradient-descent (7)
- domain-shifts (7)
- sparsity (7)
- self-reflection (7)
- human-ai-collaboration (7)
- accuracy-improvement (7)
- theoretical-guarantees (7)
- causal-inference (7)
- pattern-recognition (7)
- denoising (7)
- privacy (7)
- experiments (7)
- complex-reasoning-tasks (7)
- experimental-results (7)
- memory-efficiency (7)
- transformer-architecture (7)
- language-modeling (7)
- model-compression (7)
- cifar-10 (7)
- quantum-computing (7)
- kullback-leibler-divergence (7)
- training-dynamics (7)
- personalization (7)
- mixture-of-experts (7)
- classifier-free-guidance (7)
- dataset-creation (7)
- knowledge-editing (7)
- 3d-reconstruction (7)
- video-generation (7)
- safety (7)
- representation-learning (7)
- autonomous-agents (6)
- uncertainty-estimation (6)
- prediction-accuracy (6)
- autonomous-systems (6)
- natural-language-understanding (6)
- offline-reinforcement-learning (6)
- dataset-construction (6)
- pretraining (6)
- embedding-space (6)
- data-synthesis (6)
- latent-representations (6)
- reliability (6)
- convergence (6)
- image-restoration (6)
- transformer-based-architectures (6)
- retrieval-performance (6)
- flow-matching (6)
- data-quality (6)
- model-evaluation (6)
- gender-bias (6)
- multi-step-reasoning (6)
- complex-reasoning (6)
- digital-twins (6)
- semantic-segmentation (6)
- human-preferences (6)
- multi-modal-large-language-models (6)
- adaptability (6)
- loss-functions (6)
- vulnerabilities (6)
- variational-inference (6)
- synthetic-data-generation (6)
- inverse-problems (6)
- acoustic-features (6)
- classification-tasks (6)
- learning-efficiency (6)
- generalizability (6)
- reward-models (6)
- human-feedback (6)
- multi-agent-framework (6)
- self-attention-mechanism (6)
- simulation (6)
- evaluation (6)
- planning (6)
- adversarial-robustness (6)
- autoregressive-models (6)
- empirical-results (6)
- evaluation-methods (6)
- multimodal-dataset (6)
- neural-network-architecture (6)
- latent-diffusion-models (6)
- autoencoder (6)
- model-merging (6)
- data-collection (6)
- zero-shot-generalization (6)
- clustering (6)
- reproducibility (6)
- temporal-consistency (6)
- action-recognition (6)
- human-annotation (6)
- inference-speed (6)
- autonomous-vehicles (6)
- gaussian-splatting (6)
- calibration (5)
- embeddings (5)
- markov-decision-process (5)
- neuroscience (5)
- computer-graphics (5)
- thompson-sampling (5)
- stochastic-differential-equations (5)
- resource-constraints (5)
- summarization (5)
- reasoning-benchmarks (5)
- small-language-models (5)
- error-analysis (5)
- speculative-decoding (5)
- data-processing (5)
- generalization-capability (5)
- event-cameras (5)
- pre-trained-models (5)
- generalization-performance (5)
- diffusion-transformer (5)
- sparse-autoencoders (5)
- inference-efficiency (5)
- cybersecurity (5)
- ethics (5)
- cultural-contexts (5)
- model-accuracy (5)
- anomaly-detection (5)
- internet-of-things (5)
- training-data (5)
- misinformation (5)
- natural-language-inference (5)
- binary-classification (5)
- vision-foundation-models (5)
- time-series-analysis (5)
- link-prediction (5)
- approximation-error (5)
- reinforcement-learning-from-human-feedback (5)
- large-reasoning-models (5)
- neural-architectures (5)
- user-preferences (5)
- normalizing-flows (5)
- occlusions (5)
- ai-systems (5)
- optimal-transport (5)
- signal-to-noise-ratio (5)
- ai (5)
- transformer-models (5)
- future-research-directions (5)
- empirical-analysis (5)
- empirical-validation (5)
- prediction (5)
- training-efficiency (5)
- speech-recognition (5)
- motion-planning (5)
- real-time-processing (5)
- reasoning-models (5)
- data-efficiency (5)
- recurrent-neural-networks (5)
- benchmark-performance (5)
- multimodal-models (5)
- augmented-reality (5)
- state-space-models (5)
- remote-sensing (5)
- annotations (5)
- temporal-dynamics (5)
- high-dimensional-data (5)
- semantic-consistency (5)
- finance (5)
- optimization-algorithms (5)
- state-of-the-art-models (5)
- ablation-studies (5)
- instruction-following (5)
- cross-entropy-loss (5)
- semantic-features (5)
- state-of-the-art-methods (5)
- diversity (5)
- regression (5)
- inference-latency (5)
- domain-adaptation (5)
- autonomous-navigation (5)
- model-selection (5)
- benchmark-experiments (5)
- real-time-rendering (5)
- visual-quality (5)
- collision-avoidance (5)
- temporal-reasoning (5)
- multimodal-data (5)
- gpt-2 (5)
- meta-learning (5)
- clustering-algorithms (5)
- gaussian-mixture-models (5)
- semantic-alignment (5)
- learning-algorithms (5)
- monte-carlo-tree-search (5)
- confidence-intervals (5)
- attention-heads (5)
- temporal-resolution (5)
- state-of-the-art-results (5)
- spatial-reasoning (5)
- optimization-problems (5)
- data-distribution (5)
- data-generation (5)
- ai-safety (4)
- lstm (4)
- model-calibration (4)
- diagnostic-accuracy (4)
- inference (4)
- mixture-of-experts-architecture (4)
- text-summarization (4)
- watermarking (4)
- hyperparameter-tuning (4)
- novel-view-synthesis (4)
- performance-analysis (4)
- hallucination-detection (4)
- content-moderation (4)
- imagenet (4)
- model-comparison (4)
- vision-language-action-models (4)
- training-stability (4)
- learning-based-approaches (4)
- dinov2 (4)
- medical-image-analysis (4)
- multilingual-datasets (4)
- error-accumulation (4)
- algorithm-performance (4)
- dynamic-programming (4)
- failure-modes (4)
- factuality (4)
- generalization-ability (4)
- ensemble-methods (4)
- fine-tuning-methods (4)
- constrained-optimization (4)
- alignment (4)
- semi-supervised-learning (4)
- knowledge-retrieval (4)
- real-time-applications (4)
- precision (4)
- unmanned-aerial-vehicles (4)
- security-risks (4)
- mutual-information (4)
- deep-learning-architectures (4)
- adversarial-training (4)
- security-vulnerabilities (4)
- performance-comparison (4)
- human-evaluation (4)
- communication-efficiency (4)
- pruning (4)
- multimodal-reasoning (4)
- mechanistic-interpretability (4)
- implicit-bias (4)
- forecasting (4)
- knowledge-graph-completion (4)
- self-attention (4)
- unsupervised-domain-adaptation (4)
- theoretical-foundations (4)
- deepfake-detection (4)
- label-noise (4)
- bayesian-models (4)
- combinatorial-optimization (4)
- reasoning-accuracy (4)
- multilingual-settings (4)
- multi-armed-bandits (4)
- conformal-prediction (4)
- image-quality (4)
- voice-conversion (4)
- evaluation-datasets (4)
- data-modalities (4)
- predictive-performance (4)
- data-fusion (4)
- predictive-accuracy (4)
- regression-tasks (4)
- information-extraction (4)
- knowledge-sharing (4)
- resource-allocation (4)
- generalisation (4)
- safety-critical-applications (4)
- image-synthesis (4)
- geometric-structure (4)
- commonsense-reasoning (4)
- empirical-risk-minimization (4)
- semantic-representations (4)
- partial-differential-equations (4)
- medical-domain (4)
- experimental-evaluation (4)
- non-iid-data (4)
- stable-diffusion (4)
- fairness-metrics (4)
- open-source-models (4)
- consistency (4)
- resource-constrained-environments (4)
- adversarial-manipulation (4)
- generative-diffusion-models (4)
- gpt-4o (4)
- mathematical-reasoning-benchmarks (4)
- speech-emotion-recognition (4)
- prompting-strategies (4)
- noise (4)
- sample-complexity (4)
- applications (4)
- gpt-4 (4)
- text-to-image-models (4)
- model-predictive-control (4)
- video-analysis (4)
- policy-gradient (4)
- positional-encoding (4)
- localization (4)
- bayesian-inference (4)
- large-multimodal-models (4)
- text-to-video-diffusion-models (4)
- probabilistic-framework (4)
- test-time-adaptation (4)
- text-embeddings (4)
- feature-representations (4)
- reconstruction-quality (4)
- visual-grounding (4)
- missing-values (4)
- artificial-general-intelligence (4)
- multi-layer-perceptron (4)
- performance-metrics (4)
- multimodal-language-models (4)
- software-engineering (4)
- evaluation-paradigm (4)
- embedding-models (4)
- pose-estimation (4)
- next-token-prediction (4)
- human-judgment (4)
- perceptual-quality (4)
- gradient-descent (4)
- chatbots (4)
- inference-cost (4)
- clinical-decision-making (4)
- human-pose-estimation (4)
- natural-language (4)
- 3d-scenes (4)
- retrieval-tasks (4)
- chain-of-thought (4)
- implicit-neural-representations (4)
- model-development (4)
- evaluation-protocols (4)
- ethical-considerations (4)
- ppo (4)
- virtual-reality (4)
- privacy-protection (4)
- generative-frameworks (4)
- multimodal-foundation-models (4)
- theory-of-mind (4)
- multilingual-benchmarks (4)
- function-approximation (4)
- deep-learning-methods (4)
- nlp (4)
- finetuning (4)
- dataset-generation (4)
- neural-operators (4)
- multi-hop-reasoning (4)
- model-interpretability (4)
- dynamical-systems (4)
- privacy-risks (4)
- generative-artificial-intelligence (4)
- grpo (4)
- generative-adversarial-networks (4)
- kl-divergence (4)
- convergence-guarantees (4)
- statistical-methods (3)
- post-training (3)
- multi-head-attention (3)
- exploration-efficiency (3)
- resource-efficiency (3)
- ai-generated-content (3)
- multilayer-perceptron (3)
- classification-performance (3)
- video-diffusion-models (3)
- image-editing (3)
- semantic-correspondence (3)
- bayesian-optimization (3)
- nlp-tasks (3)
- scientific-machine-learning (3)
- energy-efficiency (3)
- spiking-neural-networks (3)
- knowledge-graph-construction (3)
- cross-attention (3)
- draft-model (3)
- open-challenges (3)
- task-success-rate (3)
- contact-rich-manipulation (3)
- sim-to-real-transfer (3)
- trajectory-optimization (3)
- automated-evaluation (3)
- model-bias (3)
- outlier-detection (3)
- safety-risks (3)
- representation-space (3)
- thematic-analysis (3)
- recall (3)
- quantization-errors (3)
- data-leakage (3)
- roberta (3)
- probability-distribution (3)
- user-study (3)
- error-detection (3)
- kubernetes (3)
- parameter-efficiency (3)
- multi-turn-conversations (3)
- llm-performance (3)
- materials-science (3)
- distributional-shifts (3)
- open-source-llms (3)
- instruction-tuning-dataset (3)
- large-vision-models (3)
- large-language-model-agents (3)
- privacy-leakage (3)
- rgb-images (3)
- policy-models (3)
- gradient-based-optimization (3)
- real-time-performance (3)
- speech-foundation-models (3)
- low-latency (3)
- pretrained-language-models (3)
- jailbreak-attacks (3)
- training-effectiveness (3)
- depth-estimation (3)
- probabilistic-models (3)
- 6d-pose-estimation (3)
- attack-success-rate (3)
- ocr (3)
- quantitative-analysis (3)
- mental-health (3)
- parameter-space (3)
- exploration-and-exploitation (3)
- ms-coco (3)
- classification-problem (3)
- reasoning-abilities (3)
- structural-causal-model (3)
- perturbations (3)
- image-registration (3)
- molecular-dynamics-simulations (3)
- observational-data (3)
- image-deblurring (3)
- magnetic-resonance-imaging (3)
- computed-tomography (3)
- gaussian-processes (3)
- reproducing-kernel-hilbert-spaces (3)
- representer-theorem (3)
- preference-dataset (3)
- ethical-concerns (3)
- problem-solving (3)
- quality-control (3)
- bias-in-ai (3)
- logistic-regression (3)
- client-selection (3)
- scalability-challenge (3)
- information-density (3)
- quantization-aware-training (3)
- theoretical-results (3)
- adaptive-algorithms (3)
- scene-reconstruction (3)
- singular-value-decomposition (3)
- error-propagation (3)
- geometry (3)
- benchmark-framework (3)
- quantum-neural-networks (3)
- ai-agents (3)
- downstream-performance (3)
- dropout (3)
- qa-datasets (3)
- cultural-alignment (3)
- image-processing (3)
- matrix-factorization (3)
- prompt-optimization (3)
- adversarial-examples (3)
- attention-weights (3)
- facial-expressions (3)
- intellectual-property-protection (3)
- robot-learning (3)
- communication-overhead (3)
- knowledge-injection (3)
- compression-techniques (3)
- optimization-framework (3)
- out-of-distribution-detection (3)
- contextual-information (3)
- cross-modal-retrieval (3)
- training-objectives (3)
- kolmogorov-arnold-networks (3)
- ai-model (3)
- retrieval (3)
- graph-construction (3)
- reconstruction-fidelity (3)
- sample-diversity (3)
- ablation-study (3)
- social-intelligence (3)
- prediction-error (3)
- multimodal-tasks (3)
- electronic-health-records (3)
- object-recognition (3)
- training-algorithms (3)
- message-passing (3)
- llama2-7b (3)
- instruction-datasets (3)
- discriminative-features (3)
- policy-improvement (3)
- medical-applications (3)
- annotation-pipeline (3)
- multi-agent-collaboration (3)
- machine-learning-applications (3)
- preference-alignment (3)
- causal-reasoning (3)
- linear-transformation (3)
- time-series (3)
- reasoning-ability (3)
- sampling-efficiency (3)
- directed-acyclic-graph (3)
- pseudo-labeling (3)
- multimodal-learning (3)
- policy-learning (3)
- video (3)
- computational-model (3)
- resource-constrained-settings (3)
- code-reasoning (3)
- math-reasoning (3)
- kernel-density-estimation (3)
- perception (3)
- episodic-memory (3)
- training-procedures (3)
- simulation-validation (3)
- brain-computer-interfaces (3)
- real-world-applicability (3)
- error-correction (3)
- human-cognition (3)
- fine-tuned-models (3)
- high-dimensionality (3)
- training-paradigms (3)
- verification (3)
- lora (3)
- data-driven-approaches (3)
- cultural-sensitivity (3)
- text-generation-tasks (3)
- zero-shot-setting (3)
- bias (3)
- speech-processing (3)
- auditability (3)
- reward-shaping (3)
- risk-mitigation (3)
- robustness-evaluation (3)
- domain-specific-models (3)
- class-incremental-learning (3)
- model-parameters (3)
- question-answering-tasks (3)
- cyber-physical-systems (3)
- internal-representations (3)
- model-agnostic-methods (3)
- transferability (3)
- markov-chain (3)
- automated-methods (3)
- memorization (3)
- adversarial-learning (3)
- temporal-modeling (3)
- speech-models (3)
- metrics (3)
- semantic-extraction (3)
- confidence-calibration (3)
- retriever (3)
- uncertainty (3)
- model-optimization (3)
- active-learning (3)
- performance-optimization (3)
- model-based-reinforcement-learning (3)
- euclidean-distance (3)
- alignment-techniques (3)
- word-error-rate (3)
- f1-score-improvement (3)
- cognitive-science (3)
- task-performance (3)
- personalized-federated-learning (3)
- recommendation-systems (3)
- red-teaming (3)
- safety-challenge (3)
- diffusion-based-architectures (3)
- graph-convolutional-networks (3)
- static-analysis (3)
- visualizations (3)
- mllms (3)
- memory-reduction (3)
- tabular-data (3)
- transformer-encoder (3)
- posterior-distribution (3)
- 3d-environments (3)
- text-to-image-diffusion-models (3)
- latent-variable-models (3)
- softmax-function (3)
- compressed-representations (3)
- multi-objective-optimization (3)
- computer-use-agents (3)
- imitation-learning (3)
- lidar-semantic-segmentation (3)
- generalization-bounds (3)
- text-to-speech-synthesis (3)
- mri (3)
- code-switching (3)
- off-policy-evaluation (3)
- public-datasets (3)
- disease-detection (3)
- medical-images (3)
- semantic-analysis (3)
- self-supervised-models (3)
- agriculture (3)
- camera-poses (3)
- deep-networks (3)
- image-segmentation (3)
- counterfactual-reasoning (3)
- image-denoising (3)
- taxonomy (3)
- dataset-distillation (3)
- image-recognition (3)
- conditional-diffusion-models (3)
- emergency-response (3)
- autoregressive-language-models (3)
- large-language-model-llm (3)
- real-world-applications (3)
- accessibility (3)
- formal-verification (3)
- contrastive-decoding (3)
- misinformation-detection (3)
- model-size (3)
- fact-checking (3)
- model-fine-tuning (3)
- mathematical-reasoning-datasets (3)
- human-behavior (3)
- maximum-mean-discrepancy (3)
- test-time-scaling (3)
- convergence-speed (3)
- multi-modal-dataset (3)
- kernel-based-method (3)
- multi-modal-data (3)
- image-understanding (3)
- visual-perception (3)
- memory (3)
- performance-gains (3)
- dynamic-pruning (3)
- scene-understanding (3)
- linguistic-diversity (3)
- fine-grained-detection (3)
- safety-alignment (3)
- neural-architecture-search (3)
- image-encoders (3)
- temporal-coherence (3)
- latency (3)
- mobile-robots (3)
- bi-level-optimization (3)
- obstacle-avoidance (3)
- instruction-fine-tuning (3)
- reasoning-paradigms (3)
- slam (3)
- neural-combinatorial-optimization (3)
- resnet-50 (3)
- social-sciences (3)
- whisper-models (3)
- generation-quality (3)
- semantic-information (3)
- spatio-temporal-features (3)
- monte-carlo-simulations (3)
- sota-performance (3)
- research-reproducibility (2)
- model-scale (2)
- continuous-control-tasks (2)
- vision-language-benchmarks (2)
- graph-based-representations (2)
- predictive-modeling (2)
- cold-start-scenarios (2)
- partial-observations (2)
- deep-learning-framework (2)
- entropy (2)
- overconfidence (2)
- sharpness-aware-minimization (2)
- imagenet-1k (2)
- model-performance-evaluation (2)
- noisy-data (2)
- model-efficiency (2)
- natural-language-generation (2)
- large-foundation-models (2)
- intellectual-property (2)
- dynamic-graphs (2)
- heterogeneous-graphs (2)
- comparative-experiments (2)
- sampling-strategy (2)
- execution-feedback (2)
- contrastive-objectives (2)
- hardware-utilization (2)
- general-purpose-ai-assistants (2)
- modular-architecture (2)
- task-automation (2)
- video-synthesis (2)
- user-studies (2)
- vision (2)
- diffusion-based-methods (2)
- content-generation (2)
- confidence-estimation (2)
- evaluation-settings (2)
- long-form-generation (2)
- surrogate-model (2)
- deep-generative-model (2)
- false-positive-rates (2)
- prediction-quality (2)
- computational-fluid-dynamics (2)
- efficient-sampling (2)
- concept-drift (2)
- model-updates (2)
- optical-flow (2)
- embodied-agents (2)
- multi-step-tasks (2)
- long-video-understanding (2)
- neuromorphic-hardware (2)
- visual-features (2)
- geometric-methods (2)
- unsupervised-extraction (2)
- registration-accuracy (2)
- multimodal-benchmark (2)
- reasoning-complexity (2)
- temporal-graphs (2)
- attention-computation (2)
- block-sparse-attention (2)
- sparse-attention (2)
- fine-tuning-framework (2)
- image-text-alignment (2)
- natural-language-specifications (2)
- unified-model (2)
- joint-training (2)
- sequence-length (2)
- prompting (2)
- prototype-learning (2)
- usability (2)
- knowledge-gaps (2)
- layer-skipping (2)
- compression (2)
- humanoid-locomotion (2)
- robotic-tasks (2)
- external-knowledge (2)
- noisy-content (2)
- behavioral-metrics (2)
- egocentric-vision (2)
- long-tail-scenarios (2)
- domain-randomization (2)
- adam (2)
- face-recognition (2)
- social-interactions (2)
- cross-lingual-transfer (2)
- knowledge-integration (2)
- multilingual-large-language-models (2)
- heterogeneous-information (2)
- logic (2)
- emotion-detection (2)
- training-technique (2)
- kolmogorov-complexity (2)
- feature-selection (2)
- adversarial-prompts (2)
- velocity-field (2)
- complex-environments (2)
- residual-learning (2)
- information-loss (2)
- knowledge-utilization (2)
- personas (2)
- social-engineering-attacks (2)
- noise-reduction (2)
- random-forest (2)
- post-training-quantization (2)
- quantitative-experiments (2)
- copyright-infringement (2)
- systematic-reviews (2)
- data-mining-techniques (2)
- encoder-only-models (2)
- query-efficiency (2)
- machine-learning-as-a-service (2)
- model-extraction-attacks (2)
- data-confidentiality (2)
- vulnerability-evaluation (2)
- document-retrieval (2)
- multi-class-classification (2)
- prompt-perturbations (2)
- semantic-heterogeneity (2)
- clinical-practice (2)
- accuracy-evaluation (2)
- hybrid-framework (2)
- model-weights (2)
- e-commerce (2)
- domain-specific-knowledge (2)
- molecule-optimization (2)
- multimodal-retrieval-augmented-generation (2)
- video-large-language-models (2)
- training-time (2)
- mean-squared-error (2)
- masked-language-models (2)
- speech-to-text-translation (2)
- design-principles (2)
- contextual-reasoning (2)
- prompt-injection (2)
- text-to-image-generative-models (2)
- kl-regularization (2)
- segmentation-accuracy (2)
- lora-adapters (2)
- automated-vehicles (2)
- ablation-analysis (2)
- hidden-states (2)
- modularity (2)
- multi-label-classification (2)
- medical-question-answering (2)
- correlations (2)
- neural-rendering (2)
- differentiable-rendering (2)
- corrupted-inputs (2)
- hyperparameters (2)
- complex-tasks (2)
- regularization (2)
- modality-gap (2)
- simulation-studies (2)
- real-time-predictions (2)
- robotic-manipulators (2)
- sampling-methods (2)
- latent-space-analysis (2)
- zero-shot-performance (2)
- small-datasets (2)
- pseudo-labels (2)
- faithfulness (2)
- markov-chain-monte-carlo (2)
- low-rank-approximation (2)
- automated-radiology-report-generation (2)
- chatgpt (2)
- image-captioning (2)
- automated-theorem-proving (2)
- proof-correctness (2)
- neuro-symbolic-framework (2)
- mitigation-techniques (2)
- trainable-parameters (2)
- 3d-representations (2)
- point-clouds (2)
- signed-distance-fields (2)
- landmark-detection (2)
- riemannian-manifolds (2)
- geodesics (2)
- malicious-intent (2)
- regression-model (2)
- layer-pruning (2)
- academic-integrity (2)
- feedback-mechanisms (2)
- disentangled-representations (2)
- evidence-lower-bound (2)
- coherence (2)
- heuristic-search (2)
- bayesian-optimisation (2)
- regular-expressions (2)
- multilingual-llm (2)
- translation-quality (2)
- pascal-voc (2)
- low-light-image-enhancement (2)
- thermal-images (2)
- causal-intervention (2)
- social-biases (2)
- stereotypes (2)
- speech-technologies (2)
- evaluation-system (2)
- dense-retrieval-model (2)
- natural-language-queries (2)
- material-discovery (2)
- risk-control (2)
- covariances (2)
- multimodal-contrastive-learning (2)
- probabilistic-loss-functions (2)
- data-assimilation (2)
- self-supervision (2)
- denoising-diffusion-models (2)
- drug-discovery (2)
- biomedical-research (2)
- doubly-robust-estimators (2)
- low-dimensional-representations (2)
- skip-connections (2)
- hyper-parameters (2)
- frequency-domain (2)
- satellite-data (2)
- wireless-sensor-networks (2)
- wearable-technology (2)
- industrial-safety (2)
- fall-detection (2)
- photoacoustic-image-reconstruction (2)
- svm-classifier (2)
- multi-head-attention-mechanism (2)
- residual-connections (2)
- bias-variance-trade-off (2)
- gradient-flow (2)
- random-matrix-theory (2)
- mask-generation (2)
- kernel-methods (2)
- false-discovery-rate-control (2)
- cross-domain-generalization (2)
- domain-heterogeneity (2)
- statistical-efficiency (2)
- human-intelligence (2)
- automated-analysis (2)
- large-scale-analysis (2)
- programming-languages (2)
- out-of-distribution-robustness (2)
- computer-vision-tasks (2)
- unsupervised-methods (2)
- evaluation-pipeline (2)
- collaboration (2)
- optimal-transport-problems (2)
- semantic-gap (2)
- methodologies (2)
- data-manipulation (2)
- representational-spaces (2)
- sensor-data-fusion (2)
- principal-component-analysis (2)
- approximation-algorithms (2)
- model-confidence (2)
- convergence-analysis (2)
- surrogate-modeling (2)
- physics-simulations (2)
- video-reasoning (2)
- visual-reasoning (2)
- semantic-hierarchies (2)
- text-modeling (2)
- edge-intelligence (2)
- feature-attribution (2)
- inpainting (2)
- camera-trajectories (2)
- graph-theory (2)
- cognition (2)
- algebra (2)
- verifiable-rewards (2)
- fine-tuning-llms (2)
- adaptive-frameworks (2)
- federated-fine-tuning (2)
- question-answering-datasets (2)
- mnist-dataset (2)
- active-inference (2)
- llm-based-agents (2)
- recognition-accuracy (2)
- inference-acceleration (2)
- sentence-embeddings (2)
- data-efficient-training (2)
- relative-positional-encoding (2)
- arithmetic-reasoning (2)
- length-generalization (2)
- local-fairness (2)
- electrocardiogram-analysis (2)
- multimodal-capabilities (2)
- multimodal-alignment (2)
- video-processing (2)
- interactive-experience (2)
- cost-efficiency (2)
- ai-deployments (2)
- conservation-laws (2)
- geometric-constraints (2)
- stability (2)
- gpu-usage (2)
- language-technologies (2)
- bias-research (2)
- gestures (2)
- sociability (2)
- task-execution-time (2)
- mixture-of-experts-model (2)
- image-retrieval (2)
- self-distillation (2)
- latent-diffusion (2)
- reconstruction-task (2)
- vision-and-language-tasks (2)
- adversarial-scenarios (2)
- resnet-18 (2)
- nuclear-norm (2)
- neural-network-training (2)
- gemini-25-pro (2)
- evaluation-measures (2)
- hyperparameter-optimization (2)
- interactive-learning (2)
- exploration (2)
- feature-fusion (2)
- medical-image-segmentation (2)
- audio-deepfake-detection (2)
- linear-classifier (2)
- experimental-validation (2)
- online-setting (2)
- conditional-reasoning (2)
- zero-shot-forecasting (2)
- masked-autoencoding (2)
- cost-matrix (2)
- cosine-distances (2)
- entropy-regularized-optimal-transport (2)
- statistical-frameworks (2)
- leave-one-out-cross-validation (2)
- super-resolution (2)
- earth-observation (2)
- satellite-images (2)
- credit-card-fraud-detection (2)
- reading-comprehension (2)
- model-behavior (2)
- training-convergence (2)
- challenges (2)
- models (2)
- llm-evaluation (2)
- latent-variables (2)
- gaussian-posteriors (2)
- state-estimation (2)
- decoder-only-architecture (2)
- human-computer-interaction (2)
- graph-classification (2)
- metric-learning (2)
- sparse-graphs (2)
- domain-generalization (2)
- high-resolution-image-synthesis (2)
- mask-modeling (2)
- multi-task-model (2)
- online-reinforcement-learning (2)
- empirical-experiments (2)
- feed-forward-networks (2)
- time-complexity (2)
- multi-modal-learning (2)
- perception-systems (2)
- adaptive-control-scheme (2)
- collision-free-paths (2)
- experimental-study (2)
- sampling (2)
- data-poisoning (2)
- open-domain-question-answering (2)
- learning-settings (2)
- distillation (2)
- rnns (2)
- language (2)
- self-correction (2)
- structured-reasoning (2)
- constraint-satisfaction (2)
- latent-directions (2)
- self-training (2)
- contrastive-loss (2)
- controlled-experiments (2)
- automated-metrics (2)
- text-reports (2)
- annotation-costs (2)
- explanation-quality (2)
- multimodal-framework (2)
- multimodal-representations (2)
- emotion-understanding (2)
- stylistic-features (2)
- urban-environments (2)
- dysarthric-speech (2)
- robot-manipulation (2)
- solution-quality (2)
- unlearning-techniques (2)
- proteomics (2)
- detection (2)
- clinical-tasks (2)
- memory-management (2)
- 3d-printing (2)
- gradient-updates (2)
- information-theory (2)
- adaptive-control (2)
- motion-planning-algorithms (2)
- noisy-conditions (2)
- semantic-clustering (2)
- robustness-benchmarks (2)
- cross-modal-fusion (2)
- end-to-end-training (2)
- text-embedding-models (2)
- domain-specific-data (2)
- private-datasets (2)
- multi-stage-training-pipeline (2)
- quadratic-programming (2)
- tokenization (2)
- label-efficiency (2)
- text-to-sql (2)
- motion-cues (2)
- ego4d (2)
- cost-effectiveness (2)
- machine-olfaction (2)
- textual-prompts (2)
- data-driven-approach (2)
- causal-structure-discovery (2)
- training-strategies (2)
- autoregressive-decoding (2)
- parallel-token-generation (2)
- model-aggregation (2)
- privacy-preservation (2)
- blockchain (2)
- architecture (2)
- generation (2)
- metaverse (2)
- semantic-mapping (2)
- group-dynamics (2)
- multi-hop-question-answering (2)
- eu-ai-act (2)
- sequence-models (2)
- design-guidelines (2)
- validation-loss (2)
- optimization-landscapes (2)
- high-performance-computing (2)
- semantic-similarity (2)
- dense-retrievers (2)
- mean-average-precision (2)
- scientific-discovery (2)
- nlp-benchmarks (2)
- candidate-selection (2)
- critical-reasoning (2)
- model-context-protocol (2)
- social-media-data (2)
- eeg-signals (2)
- cognitive-performance (2)
- medical-diagnosis (2)
- coordination-graphs (2)
- medical-vision-language-models (2)
- modality-misalignment (2)
- multi-turn-reasoning (2)
- structured-reasoning-process (2)
- time-series-classification (2)
- membership-inference (2)
- tabpfn (2)
- fusion-strategies (2)
- visual-perception-tasks (2)
- safety-guarantees (2)
- model-predictions (2)
- multimodal-inputs (2)
- countermeasures (2)
- text-to-speech (2)
- ai-alignment (2)
- simulation-environments (2)
- parameter-efficient-finetuning (2)
- sample-selection (2)
- case-studies (2)
- sparse-rewards (2)
- offline-data (2)
- token-compression (2)
- long-term-dependencies (2)
- egocentric-videos (2)
- spatial-coherence (2)
- conversational-ai (2)
- local-optima (2)
- semantic-embedding (2)
- neural-radiance-fields (2)
- semantic-control (2)
- auditory-scene-analysis (2)
- audio-captioning (2)
- attention-coefficients (2)
- clinical-accuracy (2)
- spatial-embeddings (2)
- out-of-domain-generalization (2)
- video-frames (2)
- extended-reality (2)
- unsupervised-representation-learning (2)
- slow-feature-analysis (2)
- neurodegenerative-disorders (2)
- missing-data (2)
- safety-mechanisms (2)
- psychological-counseling (2)
- closed-loop-simulation (2)
- sequential-editing (2)
- state-abstraction (2)
- computer-aided-design (2)
- data-mixing (2)
- robotic-control (2)
- dynamic-wireless-networks (2)
- game-theory (2)
- mechanical-properties (2)
- qa-tasks (2)
- anomaly-scores (2)
- reconstruction-errors (2)
- diffusion-based-generative-models (2)
- neuronal-activations (2)
- clip-based-architecture (2)
- surveillance-cameras (2)
- texture-preservation (2)
- compositionality (2)
- hybrid-architectures (2)
- length-extrapolation (2)
- compositional-generalization (2)
- embodied-ai (2)
- question-answering-benchmark (2)
- feature-alignment (2)
- template-free-methods (2)
- hand-object-interactions (2)
- multimodal-understanding (2)
- counterfactual-prediction (2)
- statistical-guarantees (2)
- context-aware-responses (2)
- contextual-understanding (2)
- deception-detection (2)
- output-diversity (2)
- clustering-method (2)
- visual-analysis (2)
- machine-learning-potentials (2)
- out-of-distribution-data (2)
- data-redundancy (2)
- item-response-theory (2)
- expressivity (2)
- multi-objective-reinforcement-learning (2)
- prediction-consistency (2)
- model-outputs (2)
- graph-attention-network (2)
- spatiotemporal-correlation (2)
- two-stage-training-strategy (2)
- non-autoregressive-models (2)
- safety-critical-constraints (2)
- bipartite-graphs (2)
- dynamic-graph-neural-networks (2)
- fpgas (2)
- persistent-homology (2)
- navigation (2)
- temporal-difference-algorithms (2)
- agent-interactions (2)
- optimization-challenges (2)
- cross-domain-evaluation (2)
- legged-robots (2)
- graph-based-methods (2)
- real-world-tasks (2)
- beam-search (2)
- real-time-pose-estimation (2)
- personality-traits (2)
- multimodal-dialogue (2)
- external-tools (2)
- biomedical-literature (2)
- visual-fidelity (2)
- spatial-relationships (2)
- multimodal-interactions (2)
- vegetation-indices (2)
- geospatial-analysis (2)
- hierarchical-knowledge-graphs (2)
- computational-burden (2)
- zero-shot-image-classification (2)
- differential-geometry (2)
- markov-decision-processes (2)
- invariances (2)
- synthetic-samples (2)
- math-datasets (2)
- conditional-distributions (2)
- algorithm-selection (2)
- nuscenes-benchmark (2)
- human-robot-interaction (2)
- temporal-dimensions (2)
- cultural-understanding (2)
- medical-data (2)
- animation (2)
- human-object-interaction (2)
- dynamic-objects (2)
- motion-diffusion-model (2)
- phase-transitions (2)
- high-dimensional-embeddings (2)
- action-representation (2)
- nuscenes (2)
- robust-generalization (2)
- upper-confidence-bound (2)
- attack-strategies (2)
- multi-domain-benchmark (2)
- vision-language-alignment (2)
- k-means-clustering (2)
- gpt-2-medium (2)
- domain-specific-expertise (2)
- ab-tests (2)
- nuscenes-dataset (2)
- narrative-quality (2)
- structured-data (2)
- qualitative-analysis (2)
- scaling-laws (2)
- gradient-estimation (2)
- quantum-machine-learning (2)
- variational-quantum-algorithms (2)
- simultaneous-perturbation-stochastic-approximation (2)
- hypothesis-testing (2)
- healthcare-systems (2)
- diffusion-prior (2)
- disinformation (2)
- machine-learning-algorithms (2)
- asr (2)
- ai-governance (2)
- multi-agent-environments (2)
- path-signatures (2)
- transformer-based-language-model (2)
- modular-framework (2)
- admm (2)
- unsupervised-pre-training (2)
- bilingualism (2)
- response-quality (2)
- sparsification (2)
- training-datasets (2)
- molecular-dynamics (2)
- iot-devices (2)
- audio (2)
- input-modalities (2)
- task-oriented-dialogue-systems (2)
- semantic-retrieval (2)
- defense-mechanism (2)
- cryptography (2)
- automated-evaluation-pipeline (2)
- legal-argument-generation (2)
- optimization-trajectory (2)
- constraint-enforcement (2)
- membership-inference-attacks (2)
- biomedical-domain (2)
- relational-databases (2)
- stochastic-block-model (2)
- functional-correctness (2)
- static-analysis-tools (2)
- joint-optimization (2)
- ordinary-differential-equations (2)
- parameter-estimation (2)
- power-control (2)
- data-mining (2)
- tracking-accuracy (2)
- safety-evaluations (2)
- aesthetic-quality (2)
- wasserstein-metric (2)
- model-transparency (2)
- unified-framework (2)
- control-barrier-functions (2)
- robust-algorithms (2)
- dynamic-scenes (2)
- neural-model (2)
- visual-understanding (2)
- resnet (2)
- controllable-generation (2)
- training-samples (2)
- average-precision (2)
- aggregation-strategies (2)
- probabilistic-circuits (2)
- value-functions (2)
- molecule-generation (2)
- associative-memory (2)
- semantic-association (2)
- memory-retrieval (2)
- mask-propagation (2)
- medical-benchmarks (2)
- public-health (2)
- low-rank-factorization (2)
- planning-tasks (2)
- task-alignment (2)
- curated-dataset (2)
- data-selection (2)
- music-performances (2)
- score-based-generative-models (2)
- biases (2)
- public-opinion (2)
- controllability (2)
- vehicle-detection (2)
- knowledge-retention (2)
- semantic-reasoning (2)
- semantic-similarities (2)
- spatial-information (2)
- gene-expression (2)
- hidden-markov-models (2)
- methodological-rigor (2)
- editing-accuracy (2)
- decision-making-processes (2)
- denoising-process (2)
- ai-regulation (2)
- preference-data (2)
- alignment-algorithms (2)
- named-entity-recognition (2)
- domain-specific-terminology (2)
- scaling-trend (2)
- dimension-reduction (2)
- spectral-analysis (2)
- astronomical-objects (2)
- selection-bias (2)
- distributed-learning (2)
- recommender-systems (2)
- high-dimensional-settings (2)
- score-matching (2)
- deep-learning-techniques (2)
- iterative-refinement (2)
- agentic-ai (2)
- backtracking (2)
- gaussian-noise (2)
- linear-regression (2)
- forced-alignment (2)
- neural-network-ensemble (2)
- spectral-clustering (2)
- process-reward-models (2)
- re2search (2)
- evaluation-suite (2)
- multivariate-time-series-forecasting (2)
- traffic-congestion (2)
- inductive-biases (2)
- sampling-steps (2)
- acceleration-techniques (2)
- ensemble-models (2)
- bioinformatics (2)
- intermediate-representations (2)
- temporal-knowledge (2)
- empathy (2)
- data-governance (2)
- long-short-term-memory (2)
- compiler-optimization (2)
- multimodal-systems (2)
- research-gaps (2)
- hybrid-approaches (2)
- sequential-reasoning (2)
- spatial-understanding (2)
- feature-aggregation (2)
- test-case-generation (2)
- analogical-reasoning (2)
- skeletongait (2)
- baseline-models (2)
- indian-languages (2)
- stochastic-optimization (2)
- quantile-regression (2)
- entropy-solutions (2)
- backpropagation (2)
- statistical-inference (2)
- generalist-agents (2)
- randomized-smoothing (2)
- runtime-reduction (2)
- contrastive-language-image-pre-training (2)
- text-recognition (2)
- text-classification (2)
- seathru-nerf-dataset (2)
- training-free-framework (2)
- unsupervised-clustering (2)
- time-series-datasets (2)
- regularization-method (2)
- training-methodologies (2)
- human-poses (2)
- instruction-following-data (2)
- keypoints (2)
- depth-maps (2)
- gradient-based-approximation (2)
- african-languages (2)
- low-resource-asr (2)
- predictive-power (2)
- online-hate-speech (2)
- real-world-experiments (2)
- data-filtering (2)
- data-security (2)
- alternating-minimization (2)
- socio-cultural-context (2)
- chain-of-thought-prompts (2)
- performance-saturation (2)
- data-contamination (2)
- search-algorithms (2)
- neuron-activations (2)
- ground-truth-annotations (2)
- classifier-performance (2)
- adverse-weather-conditions (2)
- wasserstein-distance (2)
- infrared-small-target-detection (2)
- decentralized-training (2)
- memory-overhead (2)
- end-to-end-speedup (2)
- causal-discovery (2)
- trends (2)
- bipedal-robots (2)
- tracking-by-detection (2)
- multi-object-tracking (2)
- graph-representation (2)
- second-order-optimization (2)
- episodic-rewards (2)
- data-enrichment (2)
- agent-performance (2)
- mujoco (2)
- human-interaction (2)
- robust-optimization (2)
- adversarial-perturbations (2)
- temporal-alignment (2)
- feature-importance (2)
- similarity-measurement (2)
- explanation-map (2)
- multimodal-data-fusion (2)
- self-supervised-representations (2)
- word-error-rate-reduction (2)
- feature-identification (2)
- hypothesis-test (2)
- signature-kernel (2)
- character-error-rate (2)
- stock-market-indices (2)
- multilingual-models (2)
- text-alignment (2)
- multi-stage-pipeline (2)
- model-utility (2)
- model-scaling (2)
- natural-language-prompts (2)
- redundancy-reduction (2)
- task-complexity (2)
- parallelization (2)
- natural-language-feedback (2)
- mitigation-strategies (2)
- multiclass-classification (2)
- partial-observability (2)
- algorithm-development (2)
- human-robot-collaboration (2)
- statistical-analysis (2)
- classifier (2)
- factual-accuracy (2)
- contextual-embeddings (2)
- flops-reduction (2)
- genomics (2)
- emotion-recognition-accuracy (2)
- factual-inconsistencies (2)
- vector-database (2)
- chain-of-thought-cot (2)
- weak-supervision (2)
- reconstruction-accuracy (2)
- expert-models (2)
- graph-contrastive-learning (2)
- state-of-the-art-systems (2)
- closed-loop-control (2)
- role-playing-prompts (2)
- information-synthesis (2)
- dpo (2)
- multimodal-generation (2)
- video-frame-interpolation (2)
- convex-optimization (2)
- image-super-resolution (2)
- deep-convolutional-neural-networks (2)
- generative-flow-networks (2)
- autonomous-robotics (2)
- safe-exploration (2)
- capacitated-vehicle-routing-problem (2)
- standardized-datasets (2)
- non-stationary-environments (2)
- learning-rate (2)
- image-manipulation (2)
- regression-discontinuity-design (2)
- 3d-geometry (2)
- diffusion-based-models (2)
- segmentation (2)
- diagnosis-tasks (2)
- data-driven-prediction (2)
- empirical-studies (2)
- functional-mri (2)
- survival-analysis (2)
- parkinsons-disease (2)
- computer-assisted-pronunciation-training (2)
- data-fidelity (2)
- cross-modal-correlations (2)
- u-net (2)
- 3d-modeling (2)
- siamese-network (2)
- path-planning (2)
- motion-quality (2)
- optical-character-recognition (2)
- mask-prediction (2)
- constraints (2)
- pretrained-models (2)
- logical-reasoning (2)
- large-models (2)
- benchmark-construction (2)
- forecasting-accuracy (2)
- temporal-dependencies (2)
- gaussian-process-regression (2)
- toxicity-detection (2)
- generalized-category-discovery (2)
- shortcut-learning (2)
- visual-language-models (2)
- hm3d-dataset (2)
- task-allocation-strategies (2)
- neural-fields (2)
- explanations (2)
- ai-agent-systems (2)
- vehicle-routing-problem (2)
- performance-benchmarks (2)
- collaborative-training (2)
- alignment-methods (2)
- adversarial-fine-tuning (2)
- learning-based-methods (2)
- language-pairs (2)
- human-label-variation (2)
- theorem-proving (2)
- ecological-monitoring (2)
- activations (2)
- exponential-moving-average (2)
- spatial-consistency (2)
- steering-vectors (2)
- long-texts (2)
- partially-relevant-video-retrieval (2)
- autoregressive-framework (2)
- vit-b-16 (2)
- vgg-16 (2)
- pareto-front (2)
- prompt-learning (2)
- cross-dataset-generalization (2)
- sample-complexity-bounds (2)
- visual-information (2)
- fixed-budget (2)
- error-probability (2)
- time-series-prediction (2)
- llama-2 (2)
- random-fourier-features (2)
- multiple-instance-learning (2)
- language-acquisition (2)
- personalized-learning (2)
- speaker-identity (2)
- dynamic-systems (2)
- few-shot-prompting (2)
- emotions (2)
- model-fairness (2)
- expressiveness (2)
- wearable-devices (2)
- question-answer-pairs (2)
- token-prediction (2)
- mathematical-discovery (2)
- model-agnostic-approach (2)
- ambiguity (2)
- scoring-accuracy (2)
- optimization-process (2)
- deberta (2)
- process-transparency (2)
- gpu-memory (2)
- detection-accuracy (2)
- code-editing (2)
- disease-diagnosis (2)
- credit-assignment (2)
- treatment-effect (2)
- hallucination-issues (2)
- token-generation (2)
- object-detection-models (2)
- real-time-object-detection (2)
- training-process (2)
- data-simulation (2)
- heuristic-methods (2)
- reflectance-maps (2)
- bilingual-models (2)
- language-learning (2)
- data-science (2)
- emotional-expression (2)
- computational-methods (2)
- llama-31 (2)
- task-planning (2)
- quantum-field-theory (2)
- explainable-artificial-intelligence (2)
- affective-computing (2)
- social-norms (2)
- cost-volumes (2)
- adaptive-fusion (2)
- long-horizon-decision-making (2)
- agentic-framework (2)
- visually-impaired (2)
- open-vocabulary-semantic-segmentation (2)
- disfluencies (2)
- governance (2)
- statistical-performance (2)
- kv-cache (2)
- automation (2)
- scheduling (2)
- chest-x-rays (2)
- Published on
- Published on
• Howard University, USA• LIACS, Leiden University, The Netherlands• Genaios, Spain• CENTAI Institute, Italy- Published on
• Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China- Published on
• School of Informatics, University of Edinburgh• Bloomberg- Published on
• Technical University of Munich, Garching, Bayern, Germany- Published on
• Soochow University, Suzhou, China• Baidu Inc., Beijing, China• Shandong University, Qingdao, China- Published on
Generating Automotive Code: Large Language Models for Software Development and Verification in Safety-Critical Systems
code-generationiterative-refinementAI-in-safety-critical-domainssafety-critical-automotive-softwareLarge-Language-Modelsstatic-verificationAdaptive-Cruise-Control-systemcomparative-benchmarkingfeedback-driven-pipelinetest-driven-developmentGenerative-Artificial-Intelligencecompliance-with-safety-standardsSoftware-Development-Lifecycle- Published on
• Department of Computer Science, University of Cape Town- Published on
• Hong Kong Polytechnic University, Hong Kong, China- Published on
• International Digital Economy Academy (IDEA)• Peking University- Published on
- Published on
- Published on
- Published on
• University of Science and Technology• Beijing University• Vietnam National University• Tsinghua University- Published on
- Published on
- Published on
Towards Better Disentanglement in Non-Autoregressive Zero-Shot Expressive Voice Conversion
speaker-identityspeaker-similarityexpressive-voice-conversionstyle-adaptationsource-timbre-leakageaugmentation-based-similarity-losscross-attentionenergy-featuresexpressive-attributesconditional-variational-autoencoderlocal-F0-informationglobal-pitch-featuresstyle-embeddingsemotion-similaritymix-style-layer-normalizationlinguistic-acoustic-disentanglementstyle-transfermultilingual-discrete-speech-unitsself-supervised-framework• Department of Computer Science, University of XYZ• Department of Electrical Engineering, University of ABC• Institute for Artificial Intelligence, University of DEF- Published on
• Unknown• Zurich University of Applied Sciences, Winterthur, Switzerland• University of Zurich, Zurich, Switzerland- Published on
- Published on
• College of Computer Science, Sichuan University- Published on
• DEMACS, University of Calabria, Via Bucci 30/B, 87036 Rende (CS), Italy• University of Calabria, Via Bucci 30/B, 87036 Rende (CS), Italy• DISIT, University of Piemonte Orientale, Viale Michel 11, 15121 Alessandria, Italy- Published on
- Published on
Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era
• politehnica Bucharest• Department of Computer Science, University of Copenhagen• Pioneer Center for AI- Published on
- Published on
- Published on
- Published on
• University of Cagliari, Italy• Ruhr University Bochum, Germany• University of Modena and Reggio Emilia, Italy- Published on
• University of Hamburg, Germany• University of Bocconi, Italy- Published on
• Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute