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 LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization WACV 2026 Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models ACL 2026 Align Video Diffusion Model with Online Video-Centric Preference Optimization WACV 2026 Hyperbolic Category Discovery CVPR 2025 VipDiff: Towards Coherent and Diverse Video Inpainting via Training-Free Denoising Diffusion Models WACV 2025 CusConcept: Customized Visual Concept Decomposition with Diffusion Models WACV 2025 EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models NAACL 2025 DenseSSM: State Space Models with Dense Hidden Connection for Efficient Large Language Models NAACL 2025 CLIMD: A Curriculum Learning Framework for Imbalanced Multimodal Diagnosis MICCAI 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 Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning ICML 2025 Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts AAAI 2025 AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation ICLR 2025 DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery ICLR 2025 Needle Threading: Can LLMs Follow Threads Through Near-Million-Scale Haystacks? ICLR 2025 BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities ICLR 2025 Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping ICCV 2025 GRAB: A Challenging GRaph Analysis Benchmark for Large Multimodal Models ICCV 2025 ICE: Intrinsic Concept Extraction from a Single Image via Diffusion Models CVPR 2025 Parallel Sequence Modeling via Generalized Spatial Propagation Network CVPR 2025 Detecting Open World Objects via Partial Attribute Assignment CVPR 2025 Mr. DETR: Instructive Multi-Route Training for Detection Transformers CVPR 2025 HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts ICLR 2025 L-Man: A Large Multi-modal Model Unifying Human-centric Tasks AAAI 2025 GAMEBoT: Transparent Assessment of LLM Reasoning in Games ACL 2025 PruneVid: Visual Token Pruning for Efficient Video Large Language Models ACL 2025 v-CLR: View-Consistent Learning for Open-World Instance Segmentation CVPR 2025 RegionDrag: Fast Region-Based Image Editing with Diffusion Models ECCV 2024 Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning NIPS 2024 Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting NIPS 2024 SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation NIPS 2024 MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers NIPS 2024 Deletion-Robust Submodular Maximization with Knapsack Constraints AAAI 2024 An Empirical Study of Scaling Law for Scene Text Recognition CVPR 2024 ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks CVPR 2024 DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models CVPR 2024 IBD-SLAM: Learning Image-Based Depth Fusion for Generalizable SLAM CVPR 2024 SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matching CVPR 2024 PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery ECCV 2024 Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning ECCV 2024 Adapt without Forgetting: Distill Proximity from Dual Teachers in Vision-Language Models ECCV 2024 ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction ECCV 2024 SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning ICLR 2024 FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition ICLR 2024 Data-efficient Large Vision Models through Sequential Autoregression ICML 2024 GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer ICML 2024 Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning ICML 2024 Rethinking Optimization and Architecture for Tiny Language Models ICML 2024 One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation NIPS 2023 Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism NIPS 2023 Species196: A One-Million Semi-supervised Dataset for Fine-grained Species Recognition NIPS 2023 Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery ICCV 2023 Network Expansion for Practical Training Acceleration CVPR 2023 Boosting Semantic Segmentation from the Perspective of Explicit Class Embeddings ICCV 2023 Masked Image Modeling With Local Multi-Scale Reconstruction CVPR 2023 SeSDF: Self-Evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction CVPR 2023 Learning Attention As Disentangler for Compositional Zero-Shot Learning CVPR 2023 HeadSculpt: Crafting 3D Head Avatars with Text NIPS 2023 Revisit the Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale NIPS 2023 Triple Eagle: Simple, Fast and Practical Budget-Feasible Mechanisms NIPS 2023 GhostRNN: Reducing State Redundancy in RNN with Cheap Operations INTERSPEECH 2023 Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation ICCV 2023 Open-Vocabulary Semantic Segmentation with Decoupled One-Pass Network ICCV 2023 Practical Parallel Algorithms for Submodular Maximization Subject to a Knapsack Constraint with Nearly Optimal Adaptivity AAAI 2023 GhostNetV2: Enhance Cheap Operation with Long-Range Attention NIPS 2022 CMT: Convolutional Neural Networks Meet Vision Transformers CVPR 2022 SharpContour: A Contour-Based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation CVPR 2022 JIFF: Jointly-Aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction CVPR 2022 Vision GNN: An Image is Worth Graph of Nodes NIPS 2022 Novel Class Discovery without Forgetting ECCV 2022 Open-Set Recognition: A Good Closed-Set Classifier is All You Need ICLR 2022 A Transformer-Based Object Detector with Coarse-Fine Crossing Representations NIPS 2022 Accelerating Sparse Convolution with Column Vector-Wise Sparsity NIPS 2022 Chromatic Correlation Clustering, Revisited NIPS 2022 Redistribution of Weights and Activations for AdderNet Quantization NIPS 2022 Patch Slimming for Efficient Vision Transformers CVPR 2022 Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation NIPS 2022 Generalized Category Discovery CVPR 2022 Hire-MLP: Vision MLP via Hierarchical Rearrangement CVPR 2022 Instance-Aware Dynamic Neural Network Quantization CVPR 2022 An Image Patch Is a Wave: Phase-Aware Vision MLP CVPR 2022 ReNAS: Relativistic Evaluation of Neural Architecture Search CVPR 2021 Augmented Shortcuts for Vision Transformers NIPS 2021 Randomized Algorithms for Submodular Function Maximization with a $k$-System Constraint ICML 2021 Learning Frequency Domain Approximation for Binary Neural Networks NIPS 2021 Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation NIPS 2021 Post-Training Quantization for Vision Transformer NIPS 2021 Dynamic Resolution Network NIPS 2021 Distilling Object Detectors via Decoupled Features CVPR 2021 Positive-Unlabeled Data Purification in the Wild for Object Detection CVPR 2021 Joint Representation Learning and Novel Category Discovery on Single- and Multi-Modal Data ICCV 2021 Transformer in Transformer NIPS 2021 Contrastive Learning Based Hybrid Networks for Long-Tailed Image Classification CVPR 2021 Dual-Resolution Correspondence Networks NIPS 2020 Automatically Discovering and Learning New Visual Categories with Ranking Statistics ICLR 2020 Anisotropic Convolutional Networks for 3D Semantic Scene Completion CVPR 2020 Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets NIPS 2020 Correspondence Networks With Adaptive Neighbourhood Consensus CVPR 2020 Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection CVPR 2020 Training Binary Neural Networks through Learning with Noisy Supervision ICML 2020 Searching for Low-Bit Weights in Quantized Neural Networks NIPS 2020 Deterministic Approximation for Submodular Maximization over a Matroid in Nearly Linear Time NIPS 2020 GhostNet: More Features From Cheap Operations CVPR 2020 Unsupervised Image Matching and Object Discovery as Optimization CVPR 2019 Self-Calibrating Deep Photometric Stereo Networks CVPR 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 Attribute Aware Pooling for Pedestrian Attribute Recognition IJCAI 2019 Learning to Discover Novel Visual Categories via Deep Transfer Clustering ICCV 2019 Positive-Unlabeled Compression on the Cloud NIPS 2019 PS-FCN: A Flexible Learning Framework for Photometric Stereo ECCV 2018 TOM-Net: Learning Transparent Object Matting From a Single Image CVPR 2018 Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN NIPS 2018 SCNet: Learning Semantic Correspondence ICCV 2017 Mirror Surface Reconstruction Under an Uncalibrated Camera CVPR 2016 A Fixed Viewpoint Approach for Dense Reconstruction of Transparent Objects CVPR 2015