Shijie Cao

Sparse Attention Adaptation for Long Reasoning

Less Is More: Fast and Accurate Reasoning with Cross-Head Unified Sparse Attention

Data Efficacy for Language Model Training

Rectified Sparse Attention for Efficient Long-Sequence Generation

SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling

SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs

Dissecting Bit-Level Scaling Laws in Quantizing Vision Generative Models