2 papers
cs.AI2026
Real-Time Aligned Reward Model beyond Semantics
Zixuan Huang, Xin Xia, Yuxi Ren +10
Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptim…
cs.CV2025
MMGenBench: Fully Automatically Evaluating LMMs from the Text-to-Image Generation Perspective
Hailang Huang, Yong Wang, Zixuan Huang +4
Large Multimodal Models (LMMs) demonstrate impressive capabilities. However, current benchmarks predominantly focus on image comprehension in specific domains, and these benchmarks…