Xuefeng Bai

Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment

Evaluating and Steering Modality Preference in Multimodal Large Language Model

Multi-Token Policy Gradient Optimization

Culture In a Frame: C$^3$B as a Comic-Based Benchmark for Multimodal Culturally Awareness

The Hidden Link Between RLHF and Contrastive Learning

From Bias to Balance: Exploring and Mitigating Spatial Bias in LVLMs

Exploring the Translation Mechanism of Large Language Models

Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin