6 papers
SCI-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification
Xiangyu Zhao, Henry Hengyuan Zhao, Yiheng Wang +7
While Process Reward Models (PRMs) have achieved remarkable success in mathematical reasoning, their application in complex scientific domains-such as biology, chemistry, and physi…
Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?
Liyang Li, Muzhi Zhu, Zhiyue Zhao +5
Humans can reproduce the viewpoint specified by a target image through active head and body motion, yet spatial intelligence in foundation models has largely been studied as passiv…
ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning
Wanghan Xu, Yuhao Zhou, Hengyuan Zhao +8
Large language models can fail in critic interaction not only by answering incorrectly, but also by abandoning an initially correct scientific solution after user criticism. This i…
AnyExperts: On-Demand Expert Allocation for Multimodal Language Models with Mixture of Expert
Yuting Gao, Wang Lan, Hengyuan Zhao +3
Multimodal Mixture-of-Experts (MoE) models offer a promising path toward scalable and efficient large vision-language systems. However, existing approaches rely on rigid routing st…
VaccineRAG: Boosting Multimodal Large Language Models' Immunity to Harmful RAG Samples
Qixin Sun, Ziqin Wang, Hengyuan Zhao +6
Retrieval Augmented Generation enhances the response accuracy of Large Language Models (LLMs) by integrating retrieval and generation modules with external knowledge, demonstrating…
LLaVA-CMoE: Towards Continual Mixture of Experts for Large Vision-Language Models
Hengyuan Zhao, Ziqin Wang, Qixin Sun +5
Mixture of Experts (MoE) architectures have recently advanced the scalability and adaptability of large language models (LLMs) for continual multimodal learning. However, efficient…