3 papers
cs.AI2026
Reinforcing VLAs in Task-Agnostic World Models
Yucen Wang, Rui Yu, Fengming Zhang +5
Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world models has emerged as an effective strategy to adapt to new tasks without costly…
cs.LG2026
Elucidating Representation Degradation Problem in Diffusion Model Training
Zhipeng Yao, Dazhou Li, Zitong Zhang +6
Diffusion models have achieved remarkable success, yet their training remains inefficient due to a severe optimization bottleneck, which we term Representation Degradation. As nois…
cs.GT2026
Common-agency Games for Multi-Objective Test-Time Alignment
Baiting Chen, Tong Zhu, Rui Yu +1
Aligning large language models (LLMs) with human preferences is inherently multi-objective: different users and evaluation criteria impose heterogeneous and often conflicting requi…