Chengsong Huang
Scholar

Chengsong Huang

Google Scholar ID: A7gPbV8AAAAJ
Washington University in St. Louis
Large Language ModelsEfficient InferenceNatural Language Processing
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
581
 
H-index
10
 
i10-index
10
 
Publications
18
 
Co-authors
5
list available
Contact
CVOpen ↗GitHubOpen ↗
Publications
24 items
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
2026
Cited
0
Process Rewards with Learned Reliability
2026
Cited
0
G-Zero: Self-Play for Open-Ended Generation from Zero Data
2026
Cited
0
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
2026
Cited
0
Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration
2026
Cited
0
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
2026
Cited
0
Training Data Efficiency in Multimodal Process Reward Models
2026
Cited
0
Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing
2026
Cited
1
Resume (English only)
Academic Achievements
  • Sep 2025: Released new papers 'Vision-SR1' and 'Parallel-R1'
  • Aug 2025: Paper 'R-Zero' featured as the second paper in HuggingFace's Daily Papers
  • Apr 2025: Passed qualifying exam; citation count reached 500
  • Published multiple papers at top-tier venues including ICLR 2025, COLM 2024, EMNLP 2023, ACL 2023, AAAI 2023, CIKM 2021, and ACL 2021
  • Served as reviewer for ARR (2024–present), AAAI 2026, ICLR 2025, and COLM (2024–present)
Co-authors
5 total
Bill Yuchen Lin
Bill Yuchen Lin
Affiliate Assistant Professor, University of Washington
Jiaxin Huang
Jiaxin Huang
Washington University in St. Louis
Xiaoqing Zheng
Xiaoqing Zheng
Fudan University
Yanghua Xiao (肖仰华)
Yanghua Xiao (肖仰华)
Professor of Computer Science, Fudan University
Wenhao Yu
Wenhao Yu
Researcher, Tencent (Seattle)