Showing 2026Show all
3 papers · 1 filter
cs.CV2026
Looks the Same, Answers Differently: Flip-Direction Steering for Robust Vision-Language Reasoning
Yeonsung Jung, Joonhyun Jeong, Hoang Pham +4
Vision-language models (VLMs) achieve strong visual reasoning performance, yet subtle changes from routine image capture and processing can alter their reasoning trajectories even…
cs.LG2026
AdvantageFlow: Regularized Advantage-Weighted RL in Flow Models
Branislav Kveton, Anup Rao, Subhojyoti Mukherjee +2
We present AdvantageFlow, a forward-process reinforcement learning (RL) algorithm for rectified flow models. The algorithm minimizes an advantage-weighted prediction loss, which ma…
cs.LG2026
Partial Policy Gradients for RL in LLMs
Puneet Mathur, Branislav Kveton, Subhojyoti Mukherjee +1
Reinforcement learning is a framework for learning to act sequentially in an unknown environment. We propose a natural approach for modeling policy structure in policy gradients. T…