Ermo Hua

FlowRL: Matching Reward Distributions for LLM Reasoning

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

LATTS: LAtent space Test Time Scaling for diffusion language models

LFQA-E: Carefully Benchmarking Long-form QA Evaluation

Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism

TTRL: Test-Time Reinforcement Learning

MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding

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

CALF: Benchmarking Evaluation of LFQA Using Chinese Examinations