Fanghao Shao — accepted AI-conference papers

2026

Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNets

Bo Xue, Yunchong Song, Fanghao Shao, Xuekai Zhu, Lin Chen, Luoyi Fu +2

ICLR 2026poster

Standard autoregressive language models generate text token-by-token from a fixed vocabulary, inducing a *tree-structured state space* when viewing token sampling as an action, which limits flexibility and expressiveness. Recent work introduces dynamic vocabulary by sampling retrieved text spans but…

Cited by 0 Source ↗Scholar ↗

2026

FlowRL: Matching Reward Distributions for LLM Reasoning

Xuekai Zhu, Daixuan Cheng, Dinghuai Zhang, Hengli Li, Kaiyan Zhang, Che Jiang +17

ICLR 2026poster

We propose FlowRL: matching the full reward distribution via flow balancing instead of solely maximizing rewards in large language model (LLM) reinforcement learning (RL). Recent advanced reasoning models adopt reward-maximizing methods (e.g., PPO and GRPO), which tend to over-optimize dominant rewa…

Cited by 0 Source ↗code ↗Scholar ↗