activity
20232026
most citedFedFed: Feature Distillation against Data Heterogeneity in Federated Learning

28 citations · 92 across the 52 of their papers we have counts for

collaborators
Showing 2026Show all

13 papers · 1 filter

cs.AI2026

Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation Enforcement

Xutao Mao, Jianing Zhu, Jinman Zhao +4

Reinforcement learning (RL) improves reasoning in vision-language models (VLMs) but can induce chain-of-thought (CoT) obfuscation: an operational, non-intentional outcome where tas…

cs.AI2026

Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment

Suqin Yuan, Runqi Lin, Muyang Li +5

Human-feedback alignment has made language models useful assistants and is commonly described as aligning them with humans. However, the responses people prefer from an AI need not…

cs.CV2026

Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection

Jun Nie, Yonggang Zhang, Tongliang Liu +3

Robust detection of generated images is critical to counter the misuse of generative models. Existing methods primarily depend on learning from human-annotated training datasets, l…

cs.AI2026

MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs

He Li, Haoang Chi, Qizhou Wang +6

Multimodal large language models (MLLMs) are trained on massive multimodal data, making data unlearning increasingly important as data owners may request the removal of specific co…

cs.AI2026

AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions

Jingwei Sun, Jianing Zhu, Yuanyi Li +3

Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-w…

cs.CL2026

Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory

Jingwei Sun, Jianing Zhu, Jiangchao Yao +2

To enable reliable long-term interaction, LLM agents require a memory system that can faithfully store, efficiently retrieve, and deeply reason over accumulated dialogue history. M…