Hansi Zeng

SFT Doesn’t Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs

When Scale is Fixed: Revisiting Pre-training Indicators for LLM Fine-tuning Performance

Enhancing LLM Reasoning with Retrieval-Augmented Logical Chains and Test-Time Adaptation

Inference Scaling for Long-Context Retrieval Augmented Generation

Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning