2026 paper archive — Xiaoyu Li

Flood and Harvest: The Provable Necessity of Trivia for Generating Valuable Mathematics via the Lens of Language Generation in the Limit

Xiaoyu Li, Andi Han, Dai Shi, Zheng Gao, Jiaojiao Jiang, Junbin Gao

arXiv:2606.14688 · 2026

Contrastive Identification and Generation in the Limit

Xiaoyu Li, Andi Han, Jiaojiao Jiang, Junbin Gao

NeurIPS 2026

On the Price of Privacy for Language Identification and Generation

Xiaoyu Li, Andi Han, Jiaojiao Jiang, Junbin Gao

NeurIPS 2026

Watermark Forensics for Generative Models: An Information-Theoretic Perspective

Xiaoyu Li, Zheng Gao, Xiaoyan Feng, Jiaojiao Jiang, Yulei Sui, Jiankun Hu

arXiv:2607.13003 · 2026

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

Bokang Zeng, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Jiaojiao Jiang

arXiv:2609.10416 · 2026

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

Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Jiaojiao Jiang, Yang Song, Yulei Sui, Zhenchang Xing, Liming Zhu

arXiv:2607.08400 · 2026

Feature Superposition in Neural Networks: From Theory to Practice

Dai Shi, Xiaoyu Li, Andi Han, José Miguel Hernández-Lobato

arXiv:2609.06862 · 2026

LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization

Bokang Zeng, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Jiaojiao Jiang

ACM MM 2026

SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermark

Rui Bao, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Yang Song, Jiaojiao Jiang

NeurIPS 2026 Workshop (Oral)

SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking

Zheng Gao, Yifan Yang, Xiaoyu Li, Xiaoyan Feng, Haoran Fan, Yang Song, Jiaojiao Jiang

BMVC 2026 (Oral)

Breaking Semantic-Aware Watermarks via LLM-Guided Coherence-Preserving Semantic Injection

Zheng Gao, Xiaoyu Li, Zhicheng Bao, Xiaoyan Feng, Jiaojiao Jiang

WWW 2026

The Price of Choosing Examples: Context Overfitting in Adaptive In-Context Learning

Xiaoyu Li, Jiangxuan Long

NeurIPS 2026

Anytime-Valid PAC-Bayes Certificates for Adaptive Test-Time Scaling

Xiaoyu Li, Jiangxuan Long

NeurIPS 2026

APR-Router: Complexity-Aware Cascade Routing for Cost-Effective LLM-Based Program Repair

Zhixiang Zhang, Zhicheng Bao, Xiaoyu Li, Jiaojiao Jiang, Qinghua Lu, Yulei Sui, Liming Zhu

ISSRE 2026

Exact Error-Compensated Pruning in Matrix Multiplication Time

Xiaoyu Li

Preprint · 2026

Fast Spectral Signing for Vector Balancing

Xiaoyu Li

Preprint · 2026

One Spectrum, Two Resources: Data–Memory Scaling in Autoregressive Prediction

Chiwun Yang, Xiaoyu Li

arXiv:2609.13500 · 2026

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

Yifan Yang, Zhaoyan Wang, Zheng Gao, Xiaoyu Li, Jiaojiao Jiang

arXiv:2609.12418 · 2026

CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search

Yifan Yang, Zhaoyan Wang, Zheng Gao, Xiaoyu Li, Jiaojiao Jiang

arXiv:2609.11884 · 2026

Low-Degree Polynomial Approximation of the Cross-Polytope

Xiaoyu Li

Preprint · 2026

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

Xiaoyu Li, Andi Han, Jiaojiao Jiang, Junbin Gao

arXiv:2609.10525 · 2026

Nearly Tight Rademacher Bounds for Sparsely Activated Neural Networks

Xiaoyu Li, Zhizhou Sha, Jiaojiao Jiang, Junbin Gao, Andi Han

arXiv:2609.09130 · 2026

Beyond Sparse Weights: When Is Attention Compressible?

Chiwun Yang, Xiaoyu Li

arXiv:2608.21541 · 2026

Optimistic Rates for Multiclass PAC Learning

Xiaoyu Li, Andi Han, Jiaojiao Jiang, Junbin Gao

arXiv:2608.10869 · 2026

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

Xiaoyu Li, Andi Han, Dai Shi, Jiaojiao Jiang, Junbin Gao

arXiv:2608.05029 · 2026

The Exact Worst-Case Tail Probability under Bounded Kurtosis

Xiaoyu Li, Andi Han, Jiaojiao Jiang, Junbin Gao

arXiv:2607.05226 · 2026

Beyond Averaging in John Ellipsoid Approximation: High-Accuracy Algorithms in the Leverage-Score Model

Xiaoyu Li, Junwei Yu, Jiaojiao Jiang, Junbin Gao, Andi Han

arXiv:2606.20082 · 2026

Sum-of-Squares Degree Barriers for the Reweighted-Hinge Method in Robust Halfspace Learning: A Christoffel-Function Characterization

Xiaoyu Li

arXiv:2606.17215 · 2026

A Categorical Atlas of Parameter-Efficient Fine-Tuning: Cones, Orbits, and Gauges

Xiaoyu Li, Zhizhou Sha, Chiwun Yang, Dai Shi

Technical report · 2026

What Pretraining and Midtraining Make Learnable from Rewards?

Chiwun Yang, Xiaoyu Li

arXiv:2609.38446 · 2026

When the Canonical Completion Is Wrong: Formalizing and Measuring the Jump in LLMs

Dai Shi, Xiaoyu Li, José Miguel Hernández-Lobato

arXiv:2608.26187 · 2026

Randomization Beats Gradient Descent in the Plane

Xiaoyu Li

Preprint · 2026

Parallel First-Order Optimization in One Dimension: A Tight Round–Width Tradeoff via Moment Shielding

Xiaoyu Li

Preprint · 2026

Scale-Adaptive Cut-and-Flow for Stationary-Point Search on Periodic Domains

Xiaoyu Li

Preprint · 2026

2026 archive

The Price of Choosing Examples: Context Overfitting in Adaptive In-Context Learning

Anytime-Valid PAC-Bayes Certificates for Adaptive Test-Time Scaling