collaborators

5 papers

cs.CV2026

Visual Information Extraction from Documents via Classification-Guided Large Vision-Language Models

Huafu Li, Guo Chen, Jia Xia +5

Visual information extraction (VIE) from visually rich documents remains challenging due to high layout variability and real-world impairments. Existing methods typically rely on s…

cs.CR2026

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models

Tianhang Zhao, Haodong Zhao, Wei Du +5

The ``Pre-train, then fine-tune'' paradigm has revolutionized Natural Language Processing (NLP). In this context, transferable backdoors pose a severe threat to the Pre-trained Lan…

cs.CR2026

ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data

Haodong Zhao, Jinming Hu, Zhaomin Wu +7

Federated Instruction Tuning (FIT) enables collaborative instruction tuning of large language models across multiple organizations (clients) in a cross-silo setting without requiri…

cs.AI2025

NCV: A Node-Wise Consistency Verification Approach for Low-Cost Structured Error Localization in LLM Reasoning

Yulong Zhang, Li Wang, Wei Du +7

Verifying multi-step reasoning in large language models is difficult due to imprecise error localization and high token costs. Existing methods either assess entire reasoning chain…

cs.CR2025

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer

Pengzhou Cheng, Wei Du, Zongru Wu +4

Although pre-training achieves remarkable performance, it suffers from task-agnostic backdoor attacks due to vulnerabilities in data and training mechanisms. These attacks can tran…