9 papers · 1 filter
Outcome-Guided On-Policy Self-Distillation
ZheXu Wang, Mao-Lin Luo, Yankun Hong +6
On-policy self-distillation (OPSD) provides denser token-level supervision and better computational efficiency than Reinforcement Learning with Verifiable Rewards (RLVR). However,…
Learning Process Rewards via Reasoning State Propagation
Kai Gan, Zi-Hao Zhou, Bo Ye +3
Process reward models (PRMs) have demonstrated notable effectiveness in test-time scaling and reinforcement learning by providing fine-grained signals for evaluating intermediate r…
RL Forgets! Towards Continual Policy Optimization
Mao-Lin Luo, Zhe-Xu Wang, Zi-Hao Zhou +4
Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks. Recent studies report that reinforcement learning is less prone to for…
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…
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…
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-…
ReCoSplat: Online Feed-Forward Gaussian Splatting via Render-and-Compare
Freeman Cheng, Botao Ye, Xueting Li +3
Online novel view synthesis requires a model to reconstruct a scene causally from a stream of observations while keeping it renderable at every moment. We present ReCoSplat, an onl…