Longhui Yu
HKU / Peking University researcher; first author of MetaMath; works on LLM math reasoning.
- Role
- researcher
- Currently at
- Independent
- twitter.com/longhuiyu98
- GitHub
- github.com/longhuiyu
- Scholar
- scholar.google.com/citations
- Papers
- 9
Cite
Notes
Only stored in your browser.
Authored papers
9Kimi K2.5: Visual Agentic Intelligence
arXiv 2026
Kimi-VL Technical Report
arXiv 2025
Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning
arXiv 2025
Kimi k1.5: Scaling Reinforcement Learning with LLMs
arXiv 2025
Kimi Linear: An Expressive, Efficient Attention Architecture
arXiv 2025
NuminaMath: The Largest Public Dataset in AI4Maths with 860k Pairs of Competition Math Problems and Solutions
blog
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
arXiv 2024
DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality
CVPR 2023 1
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
arXiv 2023
Affiliations
Frequent co-authors
10from 9 papers