activity
20242026
collaborators

10 papers

cs.LG2026

Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1

With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…

cs.CL2025

Steering Multimodal Large Language Models Decoding for Context-Aware Safety

Zheyuan Liu, Zhangchen Xu, Guangyao Dou +4

Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet their ability to make context-aware safety decisions remains limited. Existing me…

cs.LG2025

Pre-trained Models Perform the Best When Token Distributions Follow Zipf's Law

Yanjin He, Qingkai Zeng, Meng Jiang

Tokenization is a fundamental step in natural language processing (NLP) and other sequence modeling domains, where the choice of vocabulary size significantly impacts model perform…

cs.CL2025

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models

Zheyuan Liu, Guangyao Dou, Xiangchi Yuan +3

Generative models such as Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) trained on massive datasets can lead them to memorize and inadvertently reveal s…

cs.SI2025

Amplifying Your Social Media Presence: Personalized Influential Content Generation with LLMs

Yuying Zhao, Yu Wang, Xueqi Cheng +5

The remarkable advancements in Large Language Models (LLMs) have revolutionized the content generation process in social media, offering significant convenience in writing tasks. H…

cs.CL2025

Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench

Zheyuan Liu, Guangyao Dou, Mengzhao Jia +4

Generative models such as Large Language Models (LLM) and Multimodal Large Language models (MLLMs) trained on massive web corpora can memorize and disclose individuals' confidentia…