Hang Yan

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

A Benchmark for Self-Evolving Agents via Experience-Driven Lifelong Learning

SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis

Windtalkers: Watermarking Open-Source LLMs with Ciphered-Instruction

ReAttention: Training-Free Infinite Context with Finite Attention Scope

What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices

Unearthing Large Scale Domain-Specific Knowledge from Public Corpora

GAOKAO-Eval: Does High Scores Truly Reflect Strong Capabilities in LLMs?