Skip to content

Author

Xiaoyu Li

We have 9 of 18 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

TrajMark: Ownership Attribution and Segment-Level Tamper Localization for Coding-Agent Trajectories

TrajMark is proposed, a training-free, symmetric-key, visible-only trajectory watermarking framework that separates robust ownership attribution from fragile local integrity verification, and provides a design-level analysis of owner recoverability, integrity collision probability, structural overhead, and localization...

Bo-Kang Zeng, Zheng-Guang Gao, Xiao-Yu Li et al. · 1 citation
#machine learning Preprint Sep 2026

RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Search

RiPPLE provides a whole-space ranking from a fractional anchor-training budget, with comparisons interpreted under their respective evaluation and cost protocols, and the results examine ranking quality, label efficiency, architecture selection, and the roles of readout, coverage, and propagation.

Yi-Fan Yang, Zhao-Yan Wang, Zheng-Guang Gao et al. · 0 citations
#machine learning Preprint Sep 2026

Characterizing Language Generation in the Limit: Finite Witnesses and a Separation-Width Hierarchy

This work describes language generation in the limit for arbitrary families over a countable universe and describes the characterization and full width hierarchy, including the simplified normalization and a direct diagonal capture lemma.

Xiao-Yu Li, Andi Han, Jiao-Jiao Jiang et al. · 1 citation · ⚡1
#machine learning Preprint Sep 2026

DRIFT: Removing Diffusion Watermarks by Deflecting the Generative Trajectory

DRIFT, a black-box attack that combines partial forward diffusion with stochastic reverse resampling, achieves 98-100% attack success and the best image quality among the compared attacks, without secret keys, verifier internals, or per-image gradient optimization.

Rui Bao, Zheng-Guang Gao, Xiao-Yu Li et al. · 0 citations
#machine learning Preprint Sep 2026

Nearly Tight Rademacher Bounds for Sparsely Activated Neural Networks

A spherical-cap construction proves the latter claim without assuming sparsity merely on the sampling support without assuming sparsity merely on the sampling support, and obtains agnostic minimax excess-risk bounds of order up to logarithms.

Xiao-Yu Li, Zhizhou Sha, Jiao-Jiao Jiang et al. · 0 citations
Jul 2026

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

TRACE is presented, to the authors' knowledge the first agent watermark that is distortion-free in its action choices, self-synchronizing under deletion, and unconditionally invariant under rewriting, and it is proved this behavioral watermark's signal is bought with decision entropy.

Zhengguang Gao, Xiao-Yu Li, Xiao-Yang Feng et al. · 3 citations
Preprint Jul 2026

The Exact Worst-Case Tail Probability under Bounded Kurtosis

We determine exactly what a kurtosis bound buys for one-sided tail control. For the class $\mathcal{C}(\kappa)$ of real random variables with mean $0$, variance $1$, and fourth moment at most $\kappa$, the skewness left free, we compute the worst-case tail probability $V_1(t,\kappa)=\sup_{X\in\mathcal{C}(\kappa)}\mathb...

Xiaoyu Li, Andi Han, Jiaojiao Jiang et al. · 0 citations
Preprint Aug 2026

Optimistic Rates for Multiclass PAC Learning

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 with the oracle risk itself. For a class of Natarajan dimension $d_N$ and Daniely-Shalev-Shwartz dimension $d_{DS}$, the optimal excess risk...

Xiao-Yu Li, Andi Han, Jiao-Jiao Jiang et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.