7 papers
DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model
Wenhao Lin, Chenyu Yu, Xingwei Lin +6
As large language model (LLM) agents increasingly invoke external tools and interact with real-world systems, unsafe actions may cause irreversible consequences on external states,…
Interaction-Consistent Object Removal via MLLM-Based Reasoning
Ching-Kai Huang, Wen-Chieh Lin, Yan-Cen Lee
Image-based object removal often erases only the named target, leaving behind interaction evidence that renders the result semantically inconsistent. We formalize this problem as I…
ICON: Intent-Context Coupling for Efficient Multi-Turn Jailbreak Attack
Xingwei Lin, Wenhao Lin, Sicong Cao +4
Multi-turn jailbreak attacks have emerged as a critical threat to Large Language Models (LLMs), bypassing safety mechanisms by progressively constructing adversarial contexts from…
SEDA: A Self-Adapted Entity-Centric Data Augmentation for Boosting Gird-based Discontinuous NER Models
Wen-Fang Su, Hsiao-Wei Chou, Wen-Yang Lin
Named Entity Recognition (NER) is a critical task in natural language processing, yet it remains particularly challenging for discontinuous entities. The primary difficulty lies in…
Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings
Qiong Wu, Wenhao Lin, Yiyi Zhou +4
The excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation. To gain…
What Kind of Visual Tokens Do We Need? Training-free Visual Token Pruning for Multi-modal Large Language Models from the Perspective of Graph
Yutao Jiang, Qiong Wu, Wenhao Lin +2
Recent Multimodal Large Language Models(MLLMs) often use a large number of visual tokens to compensate their visual shortcoming, leading to excessive computation and obvious visual…