LONGHUI YU

longhuiyu98[at]gmail[dot]com

15521443439

China

Hey there, welcome!

I am doing Postrain at Moonshot AI (Kimi). I received my MPhil in Computer Science from Peking University.

Hiring: We're hiring interns and full-time team members. If you're excited about agentic reasoning/agentic coding—or want to build the most usable AI agents—please reach out to me.
Let's talk: I'm always eager to learn new insights. AI's potential is still largely untapped. If you're in Beijing, let's grab coffee to discuss it.

Projects

Kimi K2 Thinking
Proud to Lead Agentic Reasoning & Reasoning to develop a powerful thinking agent.

              Agent
              Reasoning
              Thinking & Action
              HLE
            

Kimi-K2-0711 & Kimi-K2-0905

Reasoning & Tool-integrated Reasoning

Moun Scaling Agent Open Source

Kimi K1.5

Thinking Pattern and Scaling multi-modality Model | Lead the Long2Short Part

RL Long2Short Pattern Exploration

Kimi Linear

Linear Attention. Just feed my postrain data

KDA Kimi Linear attention

Papers

2023

Longhui Yu*, Weisen Jiang*, Han Shi, Jincheng Yu, Zhengying Liu, Yu Zhang, James T. Kwok, Zhenguo Li, Adrian Weller, Weiyang Liu

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models.

In Submission PDF
Weiyang Liu*, Zeju Qiu*, Yao Feng**, Yuliang Xiu**, Yuxuan Xue**, Longhui Yu**, Haiwen Feng, Zhen Liu, Juyeon Heo, Songyou Peng, Yandong Wen, Michael J. Black, Adrian Weller, Bernhard Schölkopf

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization.

In Submission PDF
Weisen Jiang, Han Shi, Longhui Yu, Zhengying Liu, Yu Zhang, Zhenguo Li, James T. Kwok

Backward Reasoning in Large Language Models for Verification.

In Submission PDF
Shoukang Hu, Kaichen Zhou, Kaiyu Li, Longhui Yu, Lanqing Hong, Tianyang Hu, Zhenguo Li, Gim Hee Lee, Ziwei Liu

ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesis.

In Submission PDF
Longhui Yu, Tianyang Hu, Lanqing Hong, Zhen Liu, Adrian Weller, Weiyang Liu

Continual Learning by Modeling Intra-Class Variation.

TMLR 2023 PDF
Yuqing Wang, Yizhi Wang, Longhui Yu, Yuesheng Zhu, Zhouhui Lian

DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality.

CVPR 2023 PDF

2022

Longhui Yu, Yifan Zhang, Lanqing Hong, Fei Chen, Zhenguo Li

Dual-Curriculum Teacher for Domain-Inconsistent Object Detection in Autonomous Driving.

BMVC 2022 PDF
Longhui Yu, Zhenyu Weng, Yuqing Wang, Yuesheng Zhu

Multi-Teacher Knowledge Distillation for Incremental Implicitly-Refined Classification.

ICME 2022 (Oral) PDF
Liyuan Wang*, Xingxing Zhang*, Kuo Yang, Longhui Yu, Chongxuan Li, Lanqing Hong, Shifeng Zhang, Zhenguo Li, Yi Zhong, Jun Zhu

Memory Replay with Data Compression for Continual Learning.

ICLR 2022 PDF