Chengsong Huang

R-Zero: Self-Evolving Reasoning LLM from Zero Data

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

CaTS: Calibrated Test-Time Scaling for Efficient LLM Reasoning

Vision-SR1: Self-Rewarding Vision-Language Model via Reasoning Decomposition and Multi-Reward Policy Optimization

PosS: Position Specialist Generates Better Draft for Speculative Decoding

UniRel-R1: RL-tuned LLM Reasoning for Knowledge Graph Relational Question Answering

GOFA: A Generative One-For-All Model for Joint Graph Language Modeling

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation

Taming Overconfidence in LLMs: Reward Calibration in RLHF

Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning