collaborators

15 papers

cs.LG2026

Optimistic Rates for Multiclass PAC Learning

Xiaoyu Li, Andi Han, Jiaojiao Jiang +1

Worst-case multiclass bounds do not become smaller when the best classifier is already nearly correct: what is missing is an optimistic rate, a guarantee whose fluctuation scales w…

cs.CC2026

On Computational Hardness of Mistake-Bounded Language Generation: A Random-Oracle Query Separation

Xiaoyu Li, Andi Han, Dai Shi +2

Generation in the limit guarantees eventual generation for every countable collection of infinite languages in the model of Kleinberg and Mullainathan [KM24], while closure dimensi…

cs.CV2026

IRIS: Visual-Semantic Binding for Forgery-Resistant Watermarking of Diffusion Images

Xiaoyan Feng, Zheng Gao, Tong Guan +4

Most in-generation diffusion watermarks embed patterns independent of the image that carries them, and attackers transplant the marks onto images the generator did not produce, res…

cs.CR2026

Watermark Forensics for Generative Models: An Information-Theoretic Perspective

Xiaoyu Li, Zheng Gao, Xiaoyan Feng +3

The paper studies how to embed and detect watermarks in the outputs of generative language models, providing an information‑theoretic analysis of the trade‑offs for detection, attr…

cs.CR2026

TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Agent Trajectories

Zheng Gao, Xiaoyu Li, Xiaoyan Feng +5

LLM agents reach users through resellers, who may rebrand a developer's agent or substitute a cheaper model. When provenance is disputed, attribution rests on the trajectory log (t…

math.PR2026

The Exact Worst-Case Tail Probability under Bounded Kurtosis

Xiaoyu Li, Andi Han, Jiaojiao Jiang +1

We determine exactly what a kurtosis bound buys for one-sided tail control. For the class of real random variables with mean , variance , and fourth moment…