activity
20242026
collaborators

5 papers

cs.CV2026

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…

cs.CR2026

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…

cs.CL2025

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…

cs.CV2025

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…

cs.CV2024

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…