Yushi Bai

LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning

SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression

MMGeoLM: Hard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models

Quicksviewer: An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes

How do Transformers Learn Implicit Reasoning?

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons

CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA