Chengsong Huang
- Papers
- 18
Cite
Notes
Only stored in your browser.
Authored papers
18RelayLLM: Efficient Reasoning via Collaborative Decoding
arXiv 2026
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
arXiv 2026
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories
arXiv 2026
Process Rewards with Learned Reliability
arXiv 2026
TTCS: Test-Time Curriculum Synthesis for Self-Evolving
arXiv 2026
Training Data Efficiency in Multimodal Process Reward Models
arXiv 2026
G-Zero: Self-Play for Open-Ended Generation from Zero Data
arXiv 2026
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
arXiv 2026
Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing
arXiv 2026
Self-Rewarding Vision-Language Model via Reasoning Decomposition
arXiv 2025
POSS: Position Specialist Generates Better Draft for Speculative Decoding
arXiv 2025
VisPlay: Self-Evolving Vision-Language Models from Images
arXiv 2025
R-Zero: Self-Evolving Reasoning LLM from Zero Data
arXiv 2025
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
arXiv 2025
Efficient Test-Time Scaling via Self-Calibration
arXiv 2025
Taming Overconfidence in LLMs: Reward Calibration in RLHF
arXiv 2024
Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning
arXiv 2024
LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
arXiv 2023
Affiliations
Frequent co-authors
10from 18 papers