activity
20242026
collaborators

14 papers

cs.LG2026

Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling

Xinmu Ge, Zizhuo Zhang, Yu Huang +9

On-policy distillation (OPD) has emerged as a promising post-training technique for enhancing LLM reasoning. It is commonly believed to enable the student model to distill knowledg…

cs.CR2026

POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking

Zhangheng LI, Jianing Zhu, Junyuan Hong +4

Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on cross-modal tasks by jointly training on large-scale textual and visual data, where privacy-sen…

cs.AI2026

Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems

Jianing Zhu, Yeonju Ro, John Robertson +5

Long-lived AI agents are increasingly deployed as persistent operational systems, yet they are still evaluated like freshly initialized models. Day-one benchmarks miss a basic syst…

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.LG2026

When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search

John T. Robertson, Jianing Zhu, Haris Vikalo +1

Activation steering offers a lightweight way to control LLMs without retraining, but its effectiveness varies sharply across concepts. Prior work often reads this variability as ev…

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…