4 citations · 15 across the 24 of their papers we have counts for
25 papers
Lost in Implicit Routing: How LLM Agents Fail to Load Relevant Skills at Scale
Jinlin Liu, Wei Chen, Xiaojin Zhang
Reusable skills let LLM agents load task-specific instructions on demand, but they make execution depend on implicit routing over skill metadata. We test whether this design scales…
When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems
Yangxiao Jiang, Jiarun Fan, Mingcong Xu +6
Multi-Agent Systems (MAS) have recently moved from static workflows toward dynamically generated collaboration topologies. However, existing topology generation methods rely primar…
RIDGE: Region-Informed Derivative-Guided Evidence Selection for Long Video Understanding
Shanqing Xu, Meng Luo, Mengchen Qian +7
Long videos contain far more visual content than Large Vision-Language Models (LVLMs) can process under a fixed visual-token budget, making frame selection essential. Existing quer…
MedReaMM: Evaluating Large Multimodal Models on Expert-Level Clinical Diagnostic Synthesis
Lai Wei, Yuchao Chen, Zhenbiao Cao +5
The application of Large Language Models (LLMs) to diagnostic decision-making has garnered growing interest. However, existing benchmarks largely focus on textual reasoning or isol…
ViCrop-Det: Spatial Attention Entropy Guided Cropping for Training-Free Small-Object Detection
Hui Wang, Hongze Li, Wei Chen +1
Transformer-based architectures have established a dominant paradigm in global semantic perception; however, they remain fundamentally constrained by the profound spatial heterogen…
Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA
Yuanlei Zheng, Pei Fu, Hang Li +9
Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a tr…
Perturbation-Induced Linearization: Constructing Unlearnable Data with Solely Linear Classifiers
Jinlin Liu, Wei Chen, Xiaojin Zhang
Collecting web data to train deep models has become increasingly common, raising concerns about unauthorized data usage. To mitigate this issue, unlearnable examples introduce impe…
AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale
Ziyang Wang, Yuanlei Zheng, Zhenbiao Cao +6
For industrial-scale text-to-SQL, supplying the entire database schema to Large Language Models (LLMs) is impractical due to context window limits and irrelevant noise. Schema link…
Deciphering the Interplay between Attack and Protection Complexity in Privacy-Preserving Federated Learning
Xiaojin Zhang, Mingcong Xu, Yiming Li +2
Federated learning (FL) offers a promising paradigm for collaborative model training while preserving data privacy. However, its susceptibility to gradient inversion attacks poses…
FedSDAF: Leveraging Source Domain Awareness for Enhanced Federated Domain Generalization
Hongze Li, Zesheng Zhou, Zhenbiao Cao +3
Traditional Federated Domain Generalization (FedDG) methods focus on learning domain-invariant features or adapting to unseen target domains, often overlooking the unique knowledge…
FedEM: A Privacy-Preserving Framework for Concurrent Utility Preservation in Federated Learning
Mingcong Xu, Xiaojin Zhang, Wei Chen +1
Federated Learning (FL) enables collaborative training of models across distributed clients without sharing local data, addressing privacy concerns in decentralized systems. Howeve…
FedEAT: A Robustness Optimization Framework for Federated LLMs
Yahao Pang, Xingyuan Wu, Xiaojin Zhang +2
Significant advancements have been made by Large Language Models (LLMs) in the domains of natural language understanding and automated content creation. However, they still face pe…
InsQABench: Benchmarking Chinese Insurance Domain Question Answering with Large Language Models
Jing Ding, Kai Feng, Binbin Lin +6
The application of large language models (LLMs) has achieved remarkable success in various fields, but their effectiveness in specialized domains like the Chinese insurance industr…
Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study
Yulin Fei, Yuhui Gao, Xingyuan Xian +3
With the rise of multimodal large language models, accurately extracting and understanding textual information from video content, referred to as video based optical character reco…
Fed-AugMix: Balancing Privacy and Utility via Data Augmentation
Haoyang Li, Wei Chen, Xiaojin Zhang
Gradient leakage attacks pose a significant threat to the privacy guarantees of federated learning. While distortion-based protection mechanisms are commonly employed to mitigate t…
RSL-SQL: Robust Schema Linking in Text-to-SQL Generation
Zhenbiao Cao, Yuanlei Zheng, Zhihao Fan +3
Text-to-SQL generation aims to translate natural language questions into SQL statements. In Text-to-SQL based on large language models, schema linking is a widely adopted strategy…
MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration
Lai Wei, Wenkai Wang, Xiaoyu Shen +5
In recent advancements, multimodal large language models (MLLMs) have been fine-tuned on specific medical image datasets to address medical visual question answering (Med-VQA) task…
Mitigating Data Reconstruction Attacks in Federated Learning: Conditions, Bounds, and Theoretical Guarantees
Xiaojin Zhang, Wei Chen, Mingcong Xu +1
Privacy attacks, particularly data reconstruction attacks, pose significant challenges to federated learning despite its promise in privacy-preserving collaborative training. This…
A Unified Learn-to-Distort-Data Framework for Privacy-Utility Trade-off in Trustworthy Federated Learning
Xiaojin Zhang, Mingcong Xu, Wei Chen
In this paper, we first give an introduction to the theoretical basis of the privacy-utility equilibrium in federated learning based on Bayesian privacy definitions and total varia…
VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models
Yu Liu, Lang Gao, Mingxin Yang +4
Large Language Models (LLMs) have training corpora containing large amounts of program code, greatly improving the model's code comprehension and generation capabilities. However,…
Beyond ESM2: Graph-Enhanced Protein Sequence Modeling with Efficient Clustering
Shujian Jiao, Bingxuan Li, Lei Wang +4
Proteins are essential to life's processes, underpinning evolution and diversity. Advances in sequencing technology have revealed millions of proteins, underscoring the need for so…
Bridging Privacy and Robustness for Trustworthy Machine Learning
Xiaojin Zhang, Wei Chen
The widespread adoption of machine learning necessitates robust privacy protection alongside algorithmic resilience. While Local Differential Privacy (LDP) provides foundational gu…
FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning
Jialuo He, Wei Chen, Xiaojin Zhang
Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical het…
CauESC: A Causal Aware Model for Emotional Support Conversation
Wei Chen, Hengxu Lin, Qun Zhang +4
Emotional Support Conversation aims at reducing the seeker's emotional distress through supportive response. Existing approaches have two limitations: (1) They ignore the emotion c…