Publications (9)
OmniRAG-Agent: Agentic Omnimodal Reasoning for Low-Resource Long Audio-Video Question Answering
Yifan Zhu, Xinyu Mu, Tao Feng +3
Long-horizon omnimodal question answering answers questions by reasoning over text, images, audio, and video. Despite recent progress on OmniLLMs, low-resource long audio-video QA…
Hankel Determinants for a Deformed Laguerre Weight with Multiple Variables and Generalized Painlevé V Equation
Xinyu Mu, Shulin Lyu
We study the Hankel determinant generated by the moments of the deformed Laguerre weight function , where $x\in \left[0,+\inf…
Hankel Determinants for a Gaussian weight with Fisher-Hartwig Singularities and Generalized Painlevé IV Equation
Xinyu Mu, Shulin Lyu
We study the Hankel determinant generated by a Gaussian weight with Fisher-Hartwig singularities of root type at , . It characterizes a type of average characte…
Explaining Model Overfitting in CNNs via GMM Clustering
Hui Dou, Xinyu Mu, Mengjun Yi +3
Convolutional Neural Networks (CNNs) have demonstrated remarkable prowess in the field of computer vision. However, their opaque decision-making processes pose significant challeng…
KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search
Haoran Luo, Haihong E, Yikai Guo +7
Knowledge Base Question Answering (KBQA) aims to answer natural language questions with a large-scale structured knowledge base (KB). Despite advancements with large language model…
Optical manipulation of valley coherence via Landau level transitions in black phosphorus and WTe2 monolayers
Xinyu Mu, Shihao Li, Xiaoying Zhou +1
Valley coherence is of great significance for exploring fundamental quantum phenomena and developing next-generation valleytronic devices. Herein, we theoretically investigate the…
MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
Yihao Wang, Haoran Xu, Renjie Gu +10
The large-scale deployment of personalized healthcare agents demands memory mechanisms that are exceptionally precise, safe, and capable of long-term clinical tracking. However, ex…
ConceptFlow: Hierarchical and Fine-grained Concept-Based Explanation for Convolutional Neural Networks
Xinyu Mu, Hui Dou, Furao Shen +1
Concept-based interpretability for Convolutional Neural Networks (CNNs) aims to align internal model representations with high-level semantic concepts, but existing approaches larg…
Training Language Model to Critique for Better Refinement
Tianshu Yu, Chao Xiang, Mingchuan Yang +8
Large language models (LLMs) have demonstrated remarkable evaluation and critique capabilities, providing insightful feedback and identifying flaws in various tasks. However, limit…