2 papers
cs.SE2026
Failure-Guided Co-Evolution of Prompts and Training Data
Tianyu Yuan, Zhuzhong Qian
Automatic prompt optimization (APO) improves language-model programs by revising prompts from task feedback, yet it typically holds its training data fixed. Repeatedly optimizing a…
cs.CV2025
Denoise to Track: Harnessing Video Diffusion Priors for Robust Correspondence
Tianyu Yuan, Yuanbo Yang, Lin-Zhuo Chen +2
In this work, we introduce HeFT (Head-Frequency Tracker), a zero-shot point tracking framework that leverages the visual priors of pretrained video diffusion models. To better unde…