4 papers · 1 filter
PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning
Hee Suk Yoon, Eunseop Yoon, Ji Woo Hong +6
Reinforcement Learning with Verifiable Rewards (RLVR) traditionally relies on a sparse, outcome-based signal. Recent work shows that providing a fine-grained, model-intrinsic signa…
ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization
Hee Suk Yoon, Eunseop Yoon, Mark Hasegawa-Johnson +2
We introduce ConfPO, a method for preference learning in Large Language Models (LLMs) that identifies and optimizes preference-critical tokens based solely on the training policy's…
HEAR: Hearing Enhanced Audio Response for Video-grounded Dialogue
Sunjae Yoon, Dahyun Kim, Eunseop Yoon +3
Video-grounded Dialogue (VGD) aims to answer questions regarding a given multi-modal input comprising video, audio, and dialogue history. Although there have been numerous efforts…
TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback
Eunseop Yoon, Hee Suk Yoon, SooHwan Eom +7
Reinforcement Learning from Human Feedback (RLHF) leverages human preference data to train language models to align more closely with human essence. These human preference data, ho…