MIT HAN Lab

StreamingVLM: Real-Time Understanding for Infinite Video Streams

[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

[MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

[HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning

[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs

[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation

[ACL'20] HAT: Hardware-Aware Transformers for Efficient Natural Language Processing

[IJCV] FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention

[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training

[CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

TinyChatEngine: On-Device LLM Inference Library

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

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

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks