collaborators

12 papers

cs.AI2026

The Singularity Has a Distribution: Exact Timing Laws and Detection Limits for a Stochastic Intelligence Explosion

Xiaoyu Li, Zheng Gao, Chiwun Yang +1

Automating AI research creates a positive feedback loop between software capability and research effort. We study a stochastic realisation of this loop in which independent, positi…

cs.LG2026

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

Yifan Yang, Zhaoyan Wang, Zheng Gao +2

Neural architecture search (NAS) evaluates candidate networks, but fully training enough architectures to rank an entire space is expensive. Zero-cost proxies score architectures a…

cs.LG2026

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

Yifan Yang, Zhaoyan Wang, Zheng Gao +2

Zero-cost proxies rank architectures cheaply, but their reliability varies across search spaces. We introduce CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework com…

cs.CR2026

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

Bokang Zeng, Zheng Gao, Xiaoyu Li +2

Watermarking the final patch produced by a coding agent provides provenance evidence for the submitted artifact, but does not authenticate the visible process that produced it. Beh…

cs.CR2026

DRIFT: Removing Diffusion Watermarks by Deflecting the Generative Trajectory

Rui Bao, Zheng Gao, Xiaoyu Li +3

Diffusion watermarking embeds verifiable signals into the generative process and commonly verifies them by recovering trajectory-dependent evidence, making the marks robust to conv…

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

A watermark in a generative model's output is usually asked only whether a text is machine-made. The same mark can do more: attribute it to the user who produced it, extract a hidd…

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…

cs.LG2026

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 +3

AI systems coupled to proof assistants now generate formal mathematics at scale, and the gap between what a checker can verify and what a mathematician would value has become the b…

cs.CV2026

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

Bokang Zeng, Zheng Gao, Xiaoyu Li +2

Proactive watermarking offers a promising approach for deepfake tamper detection and localization in short-form videos. However, existing methods often decouple audio and visual ev…

cs.CV2026

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

Rui Bao, Zheng Gao, Xiaoyu Li +3

Diffusion-based watermarking methods embed verifiable marks by manipulating the initial noise or the reverse diffusion trajectory. However, these methods share a critical assumptio…

cs.CV2026

SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking

Zheng Gao, Yifan Yang, Xiaoyu Li +4

Watermarking the initial noise of diffusion models has emerged as a promising approach for image provenance, but content-independent noise patterns can be forged via inversion and…