papers

Publications (9)

cs.CL2026

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…

math-ph2024

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…

math-ph2023

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…

cs.LG2024

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…

cs.CL2025

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…

cond-mat.mes-hall2026

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…

cs.AI2026

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…

cs.LG2025

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…

cs.CL2025

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…