About
I am a PhD candidate at the University of Wisconsin–Madison, advised by Yin Li and Pedro Morgado.
My research spans computer vision and machine learning, with interests in efficient training and inference, multimodal learning, and data quality.
Selected publications
All publicationsPatch Ranking: Token Pruning as Ranking Prediction for Efficient CLIP Inference
Accelerating Augmentation Invariance Pretraining
Projects
GitHubPyramid Orchestration
File-backed orchestration for AI coding agents, using durable handoffs to keep detailed work outside the main context.
AI Agent Survey
A bilingual survey tracing the development of LLM-based agents through the problems that shaped their capabilities.
Blog
All seriesHidden-state reasoning and looped Transformers · 12 bilingual articles
Recursive self-improvement · A bilingual reading series
- 01
- 02
- 03
