activity
20242026
collaborators

19 papers

cs.CV2026

Steal the Patch Size: Adversarially Manipulate Vision-Language Models

Kai Hu, Akash Bharadwaj, Weichen Yu +1

We present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and in…

cs.LG2026

Multi-Rollout On-Policy Distillation via Peer Successes and Failures

Weichen Yu, Xiaomin Li, Yizhou Zhao +8

Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning s…

cs.CR2026

A New Framework for Cybersecurity Refusals in AI Agents

Eliot Krzysztof Jones, Mateusz Dziemian, Matt Fredrikson +1

Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domains like cybersecurity. Existin…

cs.CL2026

The Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems

Xiaoze Liu, Ruowang Zhang, Weichen Yu +7

Multi-Agent Systems (MAS) powered by Large Language Models have unlocked advanced collaborative reasoning, yet they remain bottlenecked by discrete text communication, which impose…

cs.LG2026

When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models

Xiaoze Liu, Weichen Yu, Matt Fredrikson +2

Tokenizer transplant in cross-vocabulary model composition reconstructs donor-only embedding rows as weighted combinations over shared lexical anchors and reuses those coefficients…

cs.CR2026

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

Mateusz Dziemian, Maxwell Lin, Xiaohan Fu +28

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure…