Song Han

Scaling Vision Pre-Training to 4K Resolution CVPR 2025 NVILA: Efficient Frontier Visual Language Models CVPR 2025 SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers ICLR 2025 HART: Efficient Visual Generation with Hybrid Autoregressive Transformer ICLR 2025 SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models ICLR 2025 CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models CVPR 2025 VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation ICLR 2025 DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads ICLR 2025 Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models ICLR 2025 SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity ICML 2025 Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity ICML 2025 LongVILA: Scaling Long-Context Visual Language Models for Long Videos ICLR 2025 DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space ICCV 2025 DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer ICCV 2025 SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference ICCV 2025 SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation ICCV 2025 SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer ICML 2025 COAT: Compressing Optimizer states and Activations for Memory-Efficient FP8 Training ICLR 2025 XAttention: Block Sparse Attention with Antidiagonal Scoring ICML 2025 Sparse Refinement for Efficient High-Resolution Semantic Segmentation ECCV 2024 QUEST: Query-Aware Sparsity for Efficient Long-Context LLM Inference ICML 2024 BitDelta: Your Fine-Tune May Only Be Worth One Bit NIPS 2024 DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models CVPR 2024 Condition-Aware Neural Network for Controlled Image Generation CVPR 2024 VILA: On Pre-training for Visual Language Models CVPR 2024 Efficient Streaming Language Models with Attention Sinks ICLR 2024 LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models ICLR 2024 EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction ICCV 2023 FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer CVPR 2023 SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer CVPR 2023 SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models ICML 2023 Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models NIPS 2022 Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation CVPR 2022 On-Device Training Under 256KB Memory NIPS 2022 Network Augmentation for Tiny Deep Learning ICLR 2022 Anycost GANs for Interactive Image Synthesis and Editing CVPR 2021 LocTex: Learning Data-Efficient Visual Representations From Localized Textual Supervision ICCV 2021 Memory-efficient Patch-based Inference for Tiny Deep Learning NIPS 2021 Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning NIPS 2021 MCUNet: Tiny Deep Learning on IoT Devices NIPS 2020 Lite Transformer with Long-Short Range Attention ICLR 2020 Once-for-All: Train One Network and Specialize it for Efficient Deployment ICLR 2020 DataMix: Efficient Privacy-Preserving Edge-Cloud Inference ECCV 2020 GAN Compression: Efficient Architectures for Interactive Conditional GANs CVPR 2020 TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning NIPS 2020 APQ: Joint Search for Network Architecture, Pruning and Quantization Policy CVPR 2020 HAT: Hardware-Aware Transformers for Efficient Natural Language Processing ACL 2020 Differentiable Augmentation for Data-Efficient GAN Training NIPS 2020 Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution ECCV 2020 TSM: Temporal Shift Module for Efficient Video Understanding ICCV 2019 Point-Voxel CNN for Efficient 3D Deep Learning NIPS 2019 Deep Leakage from Gradients NIPS 2019 Park: An Open Platform for Learning-Augmented Computer Systems NIPS 2019 Communication-Optimal Distributed Dynamic Graph Clustering AAAI 2019 HAQ: Hardware-Aware Automated Quantization With Mixed Precision CVPR 2019 ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware ICLR 2019 Defensive Quantization: When Efficiency Meets Robustness ICLR 2019 Improved Dynamic Graph Learning through Fault-Tolerant Sparsification ICML 2019 Path-Level Network Transformation for Efficient Architecture Search ICML 2018 Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training ICLR 2018 Efficient Sparse-Winograd Convolutional Neural Networks ICLR 2018 AMC: AutoML for Model Compression and Acceleration on Mobile Devices ECCV 2018 Learning both Weights and Connections for Efficient Neural Network NIPS 2015