3 papers
cs.CV2025
Mitigating Hallucination in Multimodal LLMs with Layer Contrastive Decoding
Bingkui Tong, Jiaer Xia, Kaiyang Zhou
Multimodal Large Language Models (MLLMs) have shown impressive perception and reasoning capabilities, yet they often suffer from hallucinations -- generating outputs that are lingu…
cs.CV2025
Bootstrapping Grounded Chain-of-Thought in Multimodal LLMs for Data-Efficient Model Adaptation
Jiaer Xia, Bingkui Tong, Yuhang Zang +2
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in interpreting images using natural language. However, without using large-scale datasets for re…
cs.CV2025
Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning
Jiaer Xia, Yuhang Zang, Peng Gao +2
Learning general-purpose reasoning capabilities has long been a challenging problem in AI. Recent research in large language models (LLMs), such as DeepSeek-R1, has shown that rein…