Liang Zhao
Scholar

Liang Zhao

Google Scholar ID: uJJ5zskAAAAJ
StepFun
MLLMLLM
Google Scholar↗
Citations & Impact
All-time
Citations
1,136
 
H-index
16
 
i10-index
18
 
Publications
20
 
Co-authors
6
list available
Contact
No contact links provided.
Publications
7 items
ARL-Tangram: Unleash the Resource Efficiency in Agentic Reinforcement Learning
2026
Cited
0
PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering
2026
Cited
0
R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging
2026
Cited
0
STEP3-VL-10B Technical Report
2026
Cited
2
JudgeRLVR: Judge First, Generate Second for Efficient Reasoning
2026
Cited
0
MiMo-V2-Flash Technical Report
arXiv.org · 2026
Cited
11
Reinforcement Learning for Chain of Thought Compression with One-Domain-to-All Generalization
arXiv.org · 2025
Cited
0
Resume (English only)
Co-authors
6 total
Zheng Ge
Zheng Ge
Senior Researcher, StepFun
Haoran Wei
Haoran Wei
Researcher, DeepSeek
Jianjian Sun
Jianjian Sun
Researcher of StepFun
Co-author 4
Co-author 4
Limin Wang
Limin Wang
Nanjing University
Yao Teng
Yao Teng
The University of Hong Kong, Nanjing University