2 papers
cs.IR2025
Solution for Meta KDD Cup'25: A Comprehensive Three-Step Framework for Vision Question Answering
Zijian Zhang, Xiaocheng Zhang, Yang Zhou +2
Vision Large Language Models (VLLMs) have improved multi-modal understanding and visual question answering (VQA), but still suffer from hallucinated answers. Multi-modal Retrieval-…
cs.CL2024
Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization
Jianing Wang, Yang Zhou, Xiaocheng Zhang +2
Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs), but the performance is still underwhelming due to too…