11 papers
RL Forgets! Towards Continual Policy Optimization
Mao-Lin Luo, Zhe-Xu Wang, Zi-Hao Zhou +4
The paper investigates catastrophic forgetting in continual post‑training of vision‑language models with reinforcement learning, introduces the MRCL benchmark, and proposes a repla…
Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints
Chenyangguang Zhang, Botao Ye, Boqi Chen +4
Controllable video generation for complex hand-object interactions is a critical step toward building visual world models. However, existing methods often struggle to achieve fine-…
DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation
Bo Ye, Xinyu Cui, Jian Zhao +2
Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks…
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
Weijie Wang, Zimu Li, Jinchuan Shi +5
Sparse-view 3D reconstruction is increasingly addressed with feed-forward splatting networks that predict explicit primitives directly from images. Yet most existing methods remain…
TIE: Time Interval Encoding for Video Generation over Events
Zhilei Shu, Shangwen Zhu, Zihang Liang +10
Director-style prompting, robotic action prediction, and interactive video agents demand temporal grounding over concurrent events -- a regime in which 68% of general clips and ove…
Sparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discovery
Bo Ye, Kai Gan, Tong Wei +1
Generalized Category Discovery (GCD) seeks to identify novel categories from unlabeled data while retaining the classification ability of seen categories. Prior GCD methods commonl…