collaborators

12 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.CL2026

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions

Diancheng Kang, Zheyuan Liu, Ningshan Ma +3

Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful…

cs.IR2026

Bridging Textual Profiles and Latent User Embeddings for Personalization

Zhaoxuan Tan, Xiang Zhai, Yan Zhu +2

Personalized systems rely on user representations to connect behavioral history with downstream recommendation applications. Existing methods typically employ either supervised lat…

cs.CL2026

DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning

Yifan Wang, Bolian Li, Junlin Wu +5

Real-world large language model deployments (e.g., conversational AI systems, code generation assistants) naturally generate abundant implicit user dissatisfaction (DSAT) signals,…

cs.CL2026

MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues

Zheyuan Liu, Dongwhi Kim, Yixin Wan +4

Multimodal large language models (MLLMs) are increasingly deployed as assistants that interact through text and images, making it crucial to evaluate contextual safety when risk de…

cs.CL2025

From Personal to Collective: On the Role of Local and Global Memory in LLM Personalization

Zehong Wang, Junlin Wu, ZHaoxuan Tan +4

Large language model (LLM) personalization aims to tailor model behavior to individual users based on their historical interactions. However, its effectiveness is often hindered by…