12 papers
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…