Paper 1

RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios

Paper 2

RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios

Paper 3

Rectify, Don't Regret: Avoiding Pitfalls of Differentiable Simulation in Trajectory Prediction

Paper 4

YOLOv10 with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection and trustworthy multimodal AI in computer vision perception

Paper 5

Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction

Paper 1

Evaluating LLM-Based Test Generation Under Software Evolution

Paper 2

Off-Policy Value-Based Reinforcement Learning for Large Language Models

Paper 3

MemCollab: Cross-Agent Memory Collaboration via Contrastive Trajectory Distillation

Paper 4

End-to-End Training for Unified Tokenization and Latent Denoising

Paper 5

UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation

Paper 1

ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment

Paper 2

Grounding Sim-to-Real Generalization in Dexterous Manipulation: An Empirical Study with Vision-Language-Action Models

Paper 3

DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models

Paper 4

UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos

Paper 5

Efficient Zero-Shot AI-Generated Image Detection

Paper 1

DexDrummer: In-Hand, Contact-Rich, and Long-Horizon Dexterous Robot Drumming

Paper 2

Make Tracking Easy: Neural Motion Retargeting for Humanoid Whole-body Control

Paper 3

ROBOGATE: Adaptive Failure Discovery for Safe Robot Policy Deployment via Two-Stage Boundary-Focused Sampling

Paper 4

Sim-to-Real of Humanoid Locomotion Policies via Joint Torque Space Perturbation Injection

Paper 5

Evaluating Factor-Wise Auxiliary Dynamics Supervision for Latent Structure and Robustness in Simulated Humanoid Locomotion