collaborators

5 papers

cs.LG2026

More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges

Chenyu Zhou

Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown ans…

cs.CR2026

Certified Speculative Execution for Untrusted AI Agents

Chenyu Zhou, Qiliang Jiang, Shuning Wu +1

Hard-constrained sequential decision systems have no certified way to spend the test-time compute of modern AI: executing the multi-step drafts of a learned policy or a frozen LLM…

cs.AI2026

The Verifier is the Curriculum: Execution-Gated Self-Distillation for Cross-Family Game Generation

Chenyu Zhou, Qiliang Jiang, Shuning Wu +1

Post-training a code generator against a learned judge can optimize proxy features that raise the score without improving the artifact. We study the opposite signal: a deterministi…

cs.LG2026

Mechanism-Guided Selective Unlearning for RLVR-Induced Reasoning

Chenyu Zhou, Qiliang Jiang, Shuning Wu +1

We propose MAST (Mechanism-Aligned Selective Targeting), a mechanism-guided method for unlearning RLVR-induced reasoning with substantially lower collateral damage than standard fu…

cs.CV2026

The Vision Encoder as a Privacy Boundary: Visual-Token Side Channels in Encoder-Free Vision-Language Models

Chenyu Zhou, Qiliang Jiang, Shuning Wu +1

A vision encoder compresses image pixels into semantic embeddings, implicitly acting as a privacy boundary by preserving semantic content while attenuating pixel-local detail requi…