Guangxuan Xiao

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Platform for designing and evaluating Graph Neural Networks (GNN)

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

[ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads