4 papers
Variational Feature Compression for Model-Specific Representations
Zinan Guo, Zihan Wang, Chuan Yan +3
As deep learning inference is increasingly deployed in shared and cloud-based settings, a growing concern is input repurposing, in which data submitted for one task is reused by un…
Jailbroken Frontier Models Retain Their Capabilities
Daniel Zhu, Zihan Wang, Xuchan Bao +1
As language model safeguards become more robust, attackers are pushed toward developing increasingly complex jailbreaks. Prior work has found that this complexity imposes a "jailbr…
RAGEN-2: Reasoning Collapse in Agentic RL
Zihan Wang, Chi Gui, Xing Jin +13
RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track reasoning stability. Howeve…
Imprompter: Tricking LLM Agents into Improper Tool Use
Xiaohan Fu, Shuheng Li, Zihan Wang +4
Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more gen…