collaborators

6 papers

cs.CL2025

VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues

Jianshu Zhang, Dongyu Yao, Renjie Pi +2

Visually linking matching cues is a crucial ability in daily life, such as identifying the same person in multiple photos based on their cues, even without knowing who they are. De…

cs.CV2024

Personalized Visual Instruction Tuning

Renjie Pi, Jianshu Zhang, Tianyang Han +3

Recent advancements in multimodal large language models (MLLMs) have demonstrated significant progress; however, these models exhibit a notable limitation, which we refer to as "fa…

cs.CL2024

FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation

KaShun Shum, Minrui Xu, Jianshu Zhang +5

Large language models (LLMs) have become increasingly prevalent in our daily lives, leading to an expectation for LLMs to be trustworthy -- - both accurate and well-calibrated (the…

cs.CR2024

MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance

Renjie Pi, Tianyang Han, Jianshu Zhang +6

The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investiga…

cs.CV2024

Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions

Renjie Pi, Jianshu Zhang, Jipeng Zhang +3

Image description datasets play a crucial role in the advancement of various applications such as image understanding, text-to-image generation, and text-image retrieval. Currently…

cs.CR2024

FuzzLLM: A Novel and Universal Fuzzing Framework for Proactively Discovering Jailbreak Vulnerabilities in Large Language Models

Dongyu Yao, Jianshu Zhang, Ian G. Harris +1

Jailbreak vulnerabilities in Large Language Models (LLMs), which exploit meticulously crafted prompts to elicit content that violates service guidelines, have captured the attentio…