Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models Paper • 2608.18484 • Published 6 days ago • 8
From Numbers to Judgment: Specialist LLM Agents and Reinforcement Learning for European Listed Real Estate Paper • 2608.11381 • Published 14 days ago • 2
Training a Student Expert via Semi-Supervised Foundation Model Distillation Paper • 2604.03841 • Published Apr 4 • 11
NaviDriveVLM: Decoupling High-Level Reasoning and Motion Planning for Autonomous Driving Paper • 2603.07901 • Published Mar 9 • 5