22 papers
S-SPPO: Semantic-Calibrated Self-Play Preference Optimization
Xiwen Chen, Wenhui Zhu, Jingjing Wang +13
Aligning Large Language Models (LLMs) with human preferences is often formulated via Direct Preference Optimization (DPO). However, the standard Bradley-Terry instantiation of DPO…
DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning
Xiwen Chen, Wenhui Zhu, Peijie Qiu +7
Post-training LLMs with Reinforcement Learning, specifically Group Relative Policy Optimization (GRPO), has emerged as a paradigm for enhancing mathematical reasoning. However, sta…
Spatial-Conditioned Reasoning in Long-Egocentric Videos
James Tribble, Hao Wang, Si-En Hong +4
Long-horizon egocentric video presents significant challenges for visual navigation due to viewpoint drift and the absence of persistent geometric context. Although recent vision-l…
Motion Focus Recognition in Fast-Moving Egocentric Video
Si-En Hong, James Tribble, Alexander Lake +8
From Vision-Language-Action (VLA) systems to robotics, existing egocentric datasets primarily focus on action recognition tasks, while largely overlooking the inherent role of moti…
OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport
Xiwen Chen, Wenhui Zhu, Gen Li +9
Multi-modal large language models (MLLMs) achieve strong visual-language reasoning but suffer from high inference cost due to redundant visual tokens. Recent work explores visual t…
EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent
Hao Wang, Wenhui Zhu, Shao Tang +8
As a cornerstone of the modern digital economy, 3D modeling and rendering demand substantial resources and manual effort when scene editing is performed in the traditional manner.…