collaborators

15 papers

cs.CV2026

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

Yaxin Luo, Haobin Jiang, Jialv Zou +11

Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a model-harness system…

cs.LG2026

The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity

Martin J. Wainwright

We study masking diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the \emph{unmasking growth complexity} ({\textsf{UGC}\xspace}). Its l…

cs.CV2026

Simple Domain Generalization for Strong Pixel-Level Image Tampering Detection in Modern VLMs

Yi Tang, Xinyi Shang, Jiacheng Cui +12

Modern vision-language models (VLMs) have significantly improved image generation and editing capabilities, making pixel-level image tampering detection increasingly important yet…

cs.LG2026

Next-Gen CAPTCHAs: Leveraging the Cognitive Gap for Scalable and Diverse GUI-Agent Defense

Jiacheng Liu, Yaxin Luo, Jiacheng Cui +3

The rapid evolution of GUI-enabled agents has rendered traditional CAPTCHAs obsolete. While previous benchmarks like OpenCaptchaWorld established a baseline for evaluating multimod…

cs.CV2026

Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift

Jiacheng Cui, Bingkui Tong, Xinyue Bi +3

Soft labels from teacher models are a de facto practice for knowledge transfer and large-scale dataset distillation (e.g., SRe2L, LPLD). However, when we limit the number of crops…

cs.CL2026

LLMSurgeon: Diagnosing Data Mixture of Large Language Models

Yaxin Luo, Jiacheng Cui, Xiaohan Zhao +5

The pretraining data mixture of Large Language Models (LLMs) constitutes their "digital DNA", shaping model behaviors, capabilities, and failure modes. Yet this composition is rare…