Kai Han

MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers ACL 2026 PocketLLM: Ultimate Compression of Large Language Models via Meta Networks AAAI 2026 DenseSSM: State Space Models with Dense Hidden Connection for Efficient Large Language Models NAACL 2025 EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models NAACL 2025 Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts AAAI 2025 Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning ICML 2025 L-Man: A Large Multi-modal Model Unifying Human-centric Tasks AAAI 2025 LLM Data Selection and Utilization via Dynamic Bi-level Optimization ICML 2025 Mixture of Lookup Experts ICML 2025 SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs ICML 2025 Adapt without Forgetting: Distill Proximity from Dual Teachers in Vision-Language Models ECCV 2024 An Empirical Study of Scaling Law for Scene Text Recognition CVPR 2024 Data-efficient Large Vision Models through Sequential Autoregression ICML 2024 GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer ICML 2024 Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting NeurIPS 2024 Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning ICML 2024 MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers NeurIPS 2024 ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks CVPR 2024 Rethinking Optimization and Architecture for Tiny Language Models ICML 2024 Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning NeurIPS 2024 Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning ECCV 2024 Boosting Semantic Segmentation from the Perspective of Explicit Class Embeddings ICCV 2023 Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation ICCV 2023 GhostRNN: Reducing State Redundancy in RNN with Cheap Operations Interspeech 2023 Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism NeurIPS 2023 Masked Image Modeling With Local Multi-Scale Reconstruction CVPR 2023 Network Expansion for Practical Training Acceleration CVPR 2023 One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation NeurIPS 2023 Revisit the Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale NeurIPS 2023 Species196: A One-Million Semi-supervised Dataset for Fine-grained Species Recognition NeurIPS 2023 A Transformer-Based Object Detector with Coarse-Fine Crossing Representations NeurIPS 2022 Accelerating Sparse Convolution with Column Vector-Wise Sparsity NeurIPS 2022 An Image Patch Is a Wave: Phase-Aware Vision MLP CVPR 2022 CMT: Convolutional Neural Networks Meet Vision Transformers CVPR 2022 GhostNetV2: Enhance Cheap Operation with Long-Range Attention NeurIPS 2022 Hire-MLP: Vision MLP via Hierarchical Rearrangement CVPR 2022 Instance-Aware Dynamic Neural Network Quantization CVPR 2022 Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation NeurIPS 2022 Patch Slimming for Efficient Vision Transformers CVPR 2022 Redistribution of Weights and Activations for AdderNet Quantization NeurIPS 2022 Vision GNN: An Image is Worth Graph of Nodes NeurIPS 2022 Augmented Shortcuts for Vision Transformers NeurIPS 2021 Distilling Object Detectors via Decoupled Features CVPR 2021 Dynamic Resolution Network NeurIPS 2021 Learning Frequency Domain Approximation for Binary Neural Networks NeurIPS 2021 Positive-Unlabeled Data Purification in the Wild for Object Detection CVPR 2021 Post-Training Quantization for Vision Transformer NeurIPS 2021 ReNAS: Relativistic Evaluation of Neural Architecture Search CVPR 2021 Transformer in Transformer NeurIPS 2021 GhostNet: More Features From Cheap Operations CVPR 2020 Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection CVPR 2020 Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets NeurIPS 2020 Searching for Low-Bit Weights in Quantized Neural Networks NeurIPS 2020 Training Binary Neural Networks through Learning with Noisy Supervision ICML 2020 Attribute Aware Pooling for Pedestrian Attribute Recognition IJCAI 2019 Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification ICCV 2019 Co-Evolutionary Compression for Unpaired Image Translation ICCV 2019 Learning Instance-wise Sparsity for Accelerating Deep Models IJCAI 2019 Positive-Unlabeled Compression on the Cloud NeurIPS 2019 Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN NeurIPS 2018