作者位次 #3/6ICML 2026Poster· Deep Learning / Large Language Models
EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs
Chao Gong · Depeng Wang · Zhipeng Wei · Ya Guo · Huijia Zhu · Jingjing Chen
多模态OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Chao Gong · Depeng Wang · Zhipeng Wei · Ya Guo · Huijia Zhu · Jingjing Chen
Huanli Gong · Zhipeng Wei · Yu Fu · Haz Shahgir · Ananya Gupta · Yue Dong · N. Benjamin Erichson
Ziyi Gao · Zhipeng Wei · Jingjing Chen · Zhiyu Tan · Hao Li · Yi-Ping Phoebe Chen
Wenzhuo Xu · Zhipeng Wei · Zonghao Ying · Deyue Zhang · Dongdong Yang · Xiangzheng Zhang · Quanchen Zou
Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-image inputs, inadvertently introducing new vulnerabilities due to less efforts on multi-image safety alignment. Previous MLLM jailbreak methods on...
Xiafeng Man · Zhipeng Wei · Jingjing Chen