21 citations · 173 across the 53 of their papers we have counts for
7 papers · 1 filter
AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models
Haokun Chen, Jianing Li, Yao Zhang +4
Multimodal Large Language Models (MLLMs) achieve impressive performance once optimized on massive datasets. Such datasets often contain sensitive or copyrighted content, raising si…
A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space
Bingjie Zhang, Yibo Yang, Zhe Ren +4
Large language models (LLMs) have achieved remarkable success in diverse tasks, yet their safety alignment remains fragile during adaptation. Even when fine-tuning on benign data o…
Deep Research Agents Brings Deeper Harm
Shuo Chen, Zonggen Li, Xingyu Jin +8
We reveal that Deep Research (DR) agents systematically expose safety risks: simply submitting harmful queries that a standalone LLM would reject outright can elicit detailed and d…
Strong but Brittle: Simple Attacks Subvert Reasoning-based Safety Guardrails
Shuo Chen, Zhen Han, Haokun Chen +6
Open-weight Large Reasoning Models (LRMs) are approaching the capabilities of their frontier counterparts but pose significant safety concerns, as they are difficult to patch or mo…
True Multimodal In-Context Learning Needs Attention to the Visual Context
Shuo Chen, Jianzhe Liu, Zhen Han +5
Multimodal Large Language Models (MLLMs), built on powerful language backbones, have enabled Multimodal In-Context Learning (MICL)-adapting to new tasks from a few multimodal demon…
Does Machine Unlearning Truly Remove Knowledge?
Haokun Chen, Yueqi Zhang, Yuan Bi +9
In recent years, Large Language Models (LLMs) have achieved remarkable advancements, drawing significant attention from the research community. Their capabilities are largely attri…
FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings
Tong Liu, Xiao Yu, Wenxuan Zhou +2
Efficient preference optimization algorithms such as Direct Preference Optimization (DPO) have become a popular approach in aligning large language models (LLMs) with human prefere…