Scholar
Haitao Mi
Google Scholar ID: G3OMbFSm858C
Principal Researcher, Tencent US
Large Language Models
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
1,646
H-index
19
i10-index
33
Publications
20
Co-authors
51
list available
Contact
No contact links provided.
Publications
59 items
Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
2026
Cited
0
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
2026
Cited
0
Reinforcing Multimodal Reasoning Against Visual Degradation
2026
Cited
0
Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding
2026
Cited
0
Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
2026
Cited
0
Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration
2026
Cited
0
The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context
2026
Cited
0
Free(): Learning to Forget in Malloc-Only Reasoning Models
2026
Cited
0
Load more
Resume (English only)
Co-authors
51 total
Dong Yu (俞栋)
Distinguished Scientist @ Tencent AI Lab, ACM/IEEE/ISCA Fellow
Qun Liu
Noah's Ark Lab, Huawei
Lifeng Jin
Scale AI
Zhiguo Wang
Principal Scientist at AWS AI Labs
Zhaopeng Tu
Tech Lead @ Tencent Digital Human
Baolin Peng
Microsoft Research, Redmond
Linfeng Song
Tencent AI Lab | University of Rochester PhD
Ye Tian
Tencent Robotics X
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up