Xingtai Lv

FlowRL: Matching Reward Distributions for LLM Reasoning

Towards a Unified View of Large Language Model Post-Training

How Far Can Unsupervised RLVR Scale LLM Training?

MARTI: A Framework for Multi-Agent LLM Systems Reinforced Training and Inference

Process Reinforcement through Implicit Rewards

ToEdit: How to Synthesize Text Data to Avoid Model Collapse?

OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees

Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization

How to Synthesize Text Data without Model Collapse?

Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding