5 papers
Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward
Xuexiang Wen, Hang Yu, Linchao Zhu +1
While Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a promising post-training paradigm for Large Language Models (LLMs), its dependency on the gold…
IGFuse: Interactive 3D Gaussian Scene Reconstruction via Multi-Scans Fusion
Wenhao Hu, Zesheng Li, Haonan Zhou +5
Reconstructing complete and interactive 3D scenes remains a fundamental challenge in computer vision and robotics, particularly due to persistent object occlusions and limited sens…
AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding
Weili Xu, Enxin Song, Wenhao Chai +3
The challenge of long video understanding lies in its high computational complexity and prohibitive memory cost, since the memory and computation required by transformer-based LLMs…
DSG-World: Learning a 3D Gaussian World Model from Dual State Videos
Wenhao Hu, Xuexiang Wen, Xi Li +1
Building an efficient and physically consistent world model from limited observations is a long standing challenge in vision and robotics. Many existing world modeling pipelines ar…
Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field
Wenhao Hu, Wenhao Chai, Shengyu Hao +4
Achieving a consistent and compact 3D segmentation field is crucial for maintaining semantic coherence across views and accurately representing scene structures. Previous 3D scene…