6 papers
RoCo-ACE: Rollout-Conditioned Online Distillation for Retention-Aware Knowledge Injection
Yan Hong, Wei Li, Kedong Xiu +6
Knowledge injection updates pretrained MLLMs with new factual or domain-specific knowledge, but fitting full authoritative answers can cause drift in non-updated behavior. Online d…
Knowing but Not Correcting: Routine Task Requests Suppress Factual Correction in LLMs
Zixuan Chen, Hao Lin, Zizhe Chen +6
LLMs reliably correct false claims when presented in isolation, yet when the same claims are embedded in task-oriented requests, they often comply rather than correct. We term this…
Causal Probing for Internal Visual Representations in Multimodal Large Language Models
Zehao Deng, Tianjie Ju, Zheng Wu +5
Despite the remarkable success of Multimodal Large Language Models (MLLMs) across diverse tasks, the internal mechanisms governing how they encode and ground distinct visual concep…
Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
Lai Wei, Liangbo He, Jun Lan +9
Multimodal Large Language Models (MLLMs) excel at broad visual understanding but still struggle with fine-grained perception, where decisive evidence is small and easily overwhelme…
VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning
Hao Tan, Jun Lan, Senyuan Shi +6
The growing capability of video generation poses escalating security risks, making reliable detection increasingly essential. In this paper, we introduce VideoVeritas, a framework…
Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
Yanjiang Liu, Shuhen Zhou, Yaojie Lu +6
Automated red-teaming has become a crucial approach for uncovering vulnerabilities in large language models (LLMs). However, most existing methods focus on isolated safety flaws, l…