← Search

Hongyi Jin

2 accepted papers

2026

Which Reasoning Traces Are Worth Generating Further? Data Curation for Training Reasoning Models

ICML 2026poster

Supervised fine-tuning (SFT) on a small high-quality set of long reasoning traces is an effective way to enable strong reasoning abilities for Large Language Models (LLMs). However, curating a high-quality SFT data requires generating a large pool of long Chain of Thoughts (CoTs), and filtering the …

Cited by 0SourceScholar
2022

Tensor Program Optimization with Probabilistic Programs

NeurIPS 2022accept

Automatic optimization for tensor programs becomes increasingly important as we deploy deep learning in various environments, and efficient optimization relies on a rich search space and effective search. Most existing efforts adopt a search space which lacks the ability to efficiently enable domain…

Cited by 36SourcePDFScholar