Research Blogs News Tags Projects

Research

Select a Tag

Published on
April 4, 2025
ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation
View-Disentanglement-Module score-distillation multi-face-Janus-problem multi-view-rendering geometric-consistency 3D-content-creation 3D-Gaussian-Splatting zero-shot-text-to-3D-generation view-biases similarity-based-partial-order-loss
• School of Artificial Intelligence, Nanjing University of Information Science and Technology, Jiangsu 210044, China• Lenovo, Beijing, China• Department of Automation, Tsinghua University, Beijing, China
Published on
April 4, 2025
OmniCam: Unified Multimodal Video Generation via Camera Control
camera-control video-diffusion-models visual-effects OmniTr-dataset input-modalities spatio-temporally-consistent-videos multimodal-video-generation large-language-models high-quality-long-sequence-trajectories
• Zhejiang University• Shanghai Jiao Tong University• Beijing University of Technology• Jiangnan University
Published on
April 4, 2025
Improving Harmful Text Detection with Joint Retrieval and External Knowledge
AI-generated-content joint-retrieval-framework knowledge-graphs accuracy-and-robustness low-resource-training-scenarios multilingual-environments content-moderation-systems AI-safety external-contextual-information harmful-text-detection large-language-models pre-trained-language-models
Published on
April 4, 2025
Measurement of LLM’s Philosophies of Human Nature
human-nature psychological-scale trust-in-humans ethical-learning artificial-intelligence mental-loop-learning large-language-models
Published on
April 4, 2025
Causal Self-supervised Pretrained Frontend with Predictive Code for Speech Separation
real-time-streaming-applications causal-separation-models transformer-decoder-network feature-extraction self-supervised-learning speech-separation predictive-patterns
• University of Science and Technology• Tsinghua University• Peking University• Fudan University
Published on
April 4, 2025
SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks
sparsity distribution-shifts spike-dynamics temporal-processing energy-efficiency test-time-adaptation local-feature-maps generalization model-architectures Spiking-Neural-Networks robust-adaptation Artificial-Neural-Networks computational-dynamics
• Department of Electrical Engineering, City University of Hong Kong
Published on
April 4, 2025
State-of-the-Art Translation of Text-to-Gloss using mBART : A case study of Bangla
synthetic-dataset PHOENIX-14T-benchmark mBART-50 GRU text-to-gloss-translation seq-to-seq-model multi-head-attention Bangla-Sign-Language dataset-problem RNN data-augmentation State-of-the-Art-performance mBERT-multiclass-uncased
• IIT, University of Dhaka, Bangladesh• SUNY, Old Westbury, USA• Toronto Metropolitan University, Canada
Published on
April 4, 2025
FEASE: Shallow AutoEncoding Recommender with Cold Start Handling via Side Features
autoencoder cold-start-handling user-item-interaction recommendation-systems collaborative-filtering recommendation-accuracy metadata EASE-model
Published on
April 4, 2025
MultiSensor-Home: A Wide-area Multi-modal Multi-view Dataset for Action Recognition and Transformer-based Sensor Fusion
inter-view-relationships spatial-feature-learning sensor-fusion Transformer-based-methods multi-modal-action-recognition multi-view-datasets computer-vision surveillance-applications
• Graduate School of Informatics, Nagoya University, Nagoya, Aichi 464-8601, Japan• Guardian Robot Project, Information R&D and Strategy Headquarters, RIKEN, Seika, Kyoto 619-0288, Japan• Center for Artificial Intelligence, Mathematical and Data Science, Nagoya University, Nagoya, Aichi 464-8601, Japan
Published on
April 4, 2025
Moment Quantization for Video Temporal Grounding
discrete-vectors moment-codebook joint-projection-strategies moment-quantization prior-initialization feature-discrimination video-temporal-grounding clustering-process
• National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University• Multimodal Experiences Research Lab, Dolby Laboratories
Published on
April 4, 2025
Tree-based Models for Vertical Federated Learning: A Survey
design-principles privacy-protection-mechanisms label-scattering-models tree-based-models computation-protocols empirical-observations communication-protocols vertical-federated-learning feature-gathering-models
• Alibaba Group
Published on
April 4, 2025
Ga$_2$O$_3$ TCAD Mobility Parameter Calibration using Simulation Augmented Machine Learning with Physics Informed Neural Network
neural-network-(NN)Gallium-Oxide-(Ga2O3)physics-informed-neural-network-(PINN)Philips-Unified-Mobility-(PhuMob)-model Technology-Computer-Aided-Design-(TCAD)autoencoder-(AE)machine-learning Schottky-Barrier-Diode-(SBD)
Published on
April 4, 2025
LLM-Guided Evolution: An Autonomous Model Optimization for Object Detection
Mean-Average-Precision model-optimization object-detection evolutionary-algorithms image-classification automated-machine-learning You-Only-Look-Once Large-Language-Model Neural-Architecture-Search KITTI-dataset
Published on
April 4, 2025
MultiTSF: Transformer-based Sensor Fusion for Human-Centric Multi-view and Multi-modal Action Recognition
multi-view-observations video-sequence-level-recognition spatial-feature-learning human-detection sensor-fusion Transformer-based-models action-recognition frame-level-recognition multi-modal-observations
• Department of Chemical Engineering, University of XYZ• Department of Materials Science, University of ABC• Department of Chemical Engineering, University of DEF• Department of Physics, University of GHI
Published on
April 4, 2025
Beyond Conventional Transformers: The Medical X-ray Attention (MXA) Block for Improved Multi-Label Diagnosis Using Knowledge Distillation
X-ray-analysis Medical-X-ray-Attention-(MXA)-block Multi-Head-Self-Attention-(MHSA)multi-label-classification chest-X-ray-abnormality-detection Efficient-Vision-Transformer-(EfficientViT)knowledge-distillation CheXpert-dataset Medical-imaging
• Department of Mathematics, University of California, Los Angeles, Los Angeles, CA 90095
Published on
April 4, 2025
Enhancing Customer Contact Efficiency with Graph Neural Networks in Credit Card Fraud Detection Workflow
fraud-detection credit-card-fraud Relational-Graph-Convolutional-Networks user-experience customer-trust customer-contact-efficiency transaction-data false-positives
• Santa Clara University, The School of Engineering
Published on
April 4, 2025
Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models
large-language-models sample-efficiency reinforcement-learning generalization-capability kNN-based-episodic-memory chain-of-thought-prompting intrinsic-motivation episodic-memory tiny-LLMs
• Applied AI Institute, Deakin University, Australia
Published on
April 4, 2025
Generative Classifier for Domain Generalization
computer-vision-models discriminative-linear-classifier domain-generalization Gaussian-Mixture-Models Heterogeneity-Learning-Classifier Diverse-Component-Balancing Spurious-Correlation-Blocking domain-invariance domain-specific-information
• University of Science and Technology of China
Published on
April 4, 2025
MinkOcc: Towards real-time label-efficient semantic occupancy prediction
sparse-convolution-networks semi-supervised-training label-efficient-approaches vision-foundational-models LiDAR 3D-semantic-occupancy-prediction real-time-prediction autonomous-driving cameras
• Oxford Robotics Institute, Department of Engineering Science, University of Oxford• Bristol Robotics Laboratory, School of Engineering, University of the West of England
Published on
April 4, 2025
Engineering Artificial Intelligence: Framework, Challenges, and Future Direction
domain-specific-AI-approaches artificial-intelligence data-driven-contexts engineering-AI-ecosystem-framework systematic-methodologies machine-learning robustness engineering-domains scalability future-research-directions
• Center for Industrial Artificial Intelligence, Department of Mechanical Engineering, A. James Clark School of Engineering, University of Maryland, College Park, Maryland, United States of America
Published on
April 4, 2025
Advancing Semantic Caching for LLMs with Domain-Specific Embeddings and Synthetic Data
embedding-models domain-specific-embeddings computational-efficiency semantic-caching synthetic-data-generation query-latency precision empirical-evaluations
• Redis, USA• Virginia Tech
Published on
April 4, 2025
MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception
advanced-driver-assistance-systems vehicle-behavior-recognition negative-transfer traffic-context-understanding multi-axis-region-attention-network driver-behavior-recognition cross-task-knowledge-transfer multi-task-learning multimodal-learning dual-branch-multimodal-embedding driver-emotion-recognition
• Beijing Institute of Technology, Zhuhai• Tsinghua University• HKUST(GZ)• Beijing University of Chemical Technology
Published on
April 4, 2025
MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
disaggregated-expert-parallelism ping-pong-pipeline-parallelism Mixture-of-Experts M2N-communication-library computational-complexity operational-costs model-parallelism memory-intensive-architecture communication-overhead GPU-utilization large-language-models
• University of Science and Technology• Tsinghua University• Peking University• Fudan University
Published on
April 4, 2025
WonderTurbo: Generating Interactive 3D World in 0.72 Seconds
interactive-3D-generation inpainting real-time-interactivity depth-completion geometric-modeling 3D-scene-generation-framework dynamic-updates appearance-modeling spatial-consistency
• Institution1
Published on
April 4, 2025
Implicit Neural Differential Model for Spatiotemporal Dynamics
generalizability adjoint-state-methods advection-diffusion-processes reverse-mode-automatic-differentiation checkpointing-techniques numerical-stability numerical-experiments gradient-propagation-strategy spatiotemporal-dynamics multi-physics-chemical-vapor-infiltration-processes hybrid-neural-physics-modeling prediction-accuracy implicit-fixed-point-layers Burgers’-dynamics data-driven-learning error-accumulation differentiable-programming
• Department of Physics, University of XYZ• Department of Chemistry, University of ABC• Department of Materials Science, University of DEF• Department of Engineering, University of GHI
Published on
April 4, 2025
Re-thinking Temporal Search for Long-Form Video Understanding
adaptive-zooming vision-language-models long-form-video-understanding computational-efficiency visual-localization keyframe-selection benchmark-dataset temporal-search
Published on
April 4, 2025
Bipedal Robust Walking on Uneven Footholds: Piecewise Slope LIPM with Discrete Model Predictive Control
uneven-terrain Centroidal-Angular-Momentum Model-Predictive-Control Center-of-Mass-adjustment Linear-Inverted-Pendulum-Model Angular-Momentum-based-LIPM bipedal-locomotion bipedal-control Whole-Body-Controller Piecewise-Slope-LIPM
• Faculty of Computing, Harbin Institute of Technology, Harbin, 150001, China• State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, 150001, China
Published on
April 4, 2025
LLMs as Deceptive Agents: How Role-Based Prompting Induces Semantic Ambiguity in Puzzle Tasks
role-based-prompting Large-Language-Models ethical-considerations entertainment adversarial-settings educational-technologies deceptive-puzzles cognitive-load semantic-ambiguity
Published on
April 4, 2025
Adapting World Models with Latent-State Dynamics Residuals
simulation-to-reality-reinforcement-learning vision-based-MuJoCo-domains latent-state-autoregressive-world-model residual-error-function physical-robot-visual-lane-following-task residual-corrections
• Department of Biology, University of XYZ• Department of Chemistry, University of ABC• Department of Physics, University of DEF• Department of Mathematics, University of GHI
Published on
April 4, 2025
Quantum Lipschitz Bandits
elimination-based-framework Lipschitz-bandit continuous-action-spaces Zooming-algorithm stochastic-bandit-problems regret-bound quantum-computing empirical-performance quantum-Monte-Carlo non-linear-reward-functions