Picture for Fengbin Zhu

Fengbin Zhu

Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector

Add code
Oct 30, 2024
Viaarxiv icon

MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding

Add code
Oct 25, 2024
Viaarxiv icon

Large Language Models Empowered Personalized Web Agents

Add code
Oct 22, 2024
Viaarxiv icon

VideoQA in the Era of LLMs: An Empirical Study

Add code
Aug 08, 2024
Viaarxiv icon

CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG

Add code
Jun 17, 2024
Viaarxiv icon

Think Twice Before Assure: Confidence Estimation for Large Language Models through Reflection on Multiple Answers

Add code
Mar 15, 2024
Viaarxiv icon

TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data

Add code
Jan 24, 2024
Viaarxiv icon

Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents with Semantic-Oriented Hierarchical Graphs

Add code
May 04, 2023
Viaarxiv icon

Towards Complex Document Understanding By Discrete Reasoning

Add code
Jul 25, 2022
Figure 1 for Towards Complex Document Understanding By Discrete Reasoning
Figure 2 for Towards Complex Document Understanding By Discrete Reasoning
Figure 3 for Towards Complex Document Understanding By Discrete Reasoning
Figure 4 for Towards Complex Document Understanding By Discrete Reasoning
Viaarxiv icon

RDU: A Region-based Approach to Form-style Document Understanding

Add code
Jun 14, 2022
Figure 1 for RDU: A Region-based Approach to Form-style Document Understanding
Figure 2 for RDU: A Region-based Approach to Form-style Document Understanding
Figure 3 for RDU: A Region-based Approach to Form-style Document Understanding
Figure 4 for RDU: A Region-based Approach to Form-style Document Understanding
Viaarxiv icon