Bohan Zhuang

OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs AAAI 2026 Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning AAAI 2026 FPN-in-FPN: A Nested Multi-Scale Aggregation Network for Polyp Segmentation MICCAI 2025 Neighboring Autoregressive Modeling for Efficient Visual Generation ICCV 2025 ZipVL: Accelerating Vision-Language Models through Dynamic Token Sparsity ICCV 2025 ZipAR: Parallel Autoregressive Image Generation through Spatial Locality ICML 2025 Are Large Vision Language Models Good Game Players? ICLR 2025 McCaD: Multi-Contrast MRI Conditioned Adaptive Adversarial Diffusion Model for High-Fidelity MRI Synthesis WACV 2025 Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis ICCV 2025 T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching ICLR 2025 Channel Merging: Preserving Specialization for Merged Experts AAAI 2025 ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification NIPS 2024 GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI NIPS 2024 MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views NIPS 2024 MiniCache: KV Cache Compression in Depth Dimension for Large Language Models NIPS 2024 LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning ACL 2024 Efficient Stitchable Task Adaptation CVPR 2024 ModaVerse: Efficiently Transforming Modalities with LLMs CVPR 2024 Motion Mamba: Efficient and Long Sequence Motion Generation ECCV 2024 MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images ECCV 2024 LongVLM: Efficient Long Video Understanding via Large Language Models ECCV 2024 Stitched ViTs are Flexible Vision Backbones ECCV 2024 Object-Aware Inversion and Reassembly for Image Editing ICLR 2024 EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models ICLR 2024 QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models ICLR 2024 SAM-Med3D-MoE: Towards a Non-Forgetting Segment Anything Model via Mixture of Experts for 3D Medical Image Segmentation MICCAI 2024 Stitchable Neural Networks CVPR 2023 Dynamic Focus-Aware Positional Queries for Semantic Segmentation CVPR 2023 Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning ICCV 2023 BiViT: Extremely Compressed Binary Vision Transformers ICCV 2023 Mask Propagation for Efficient Video Semantic Segmentation NIPS 2023 A Survey on Efficient Training of Transformers IJCAI 2023 PTQD: Accurate Post-Training Quantization for Diffusion Models NIPS 2023 Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction NIPS 2023 Fast Vision Transformers with HiLo Attention NIPS 2022 Less Is More: Pay Less Attention in Vision Transformers AAAI 2022 EcoFormer: Energy-Saving Attention with Linear Complexity NIPS 2022 Automated Progressive Learning for Efficient Training of Vision Transformers CVPR 2022 An Efficient Spatio-Temporal Pyramid Transformer for Action Detection ECCV 2022 SA-BNN: State-Aware Binary Neural Network AAAI 2021 FATNN: Fast and Accurate Ternary Neural Networks ICCV 2021 Scalable Vision Transformers With Hierarchical Pooling ICCV 2021 AQD: Towards Accurate Quantized Object Detection CVPR 2021 Training Quantized Neural Networks With a Full-Precision Auxiliary Module CVPR 2020 Generative Low-bitwidth Data Free Quantization ECCV 2020 Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation CVPR 2019 Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs IJCAI 2019 Towards Effective Low-Bitwidth Convolutional Neural Networks CVPR 2018 Parallel Attention: A Unified Framework for Visual Object Discovery Through Dialogs and Queries CVPR 2018 Discrimination-aware Channel Pruning for Deep Neural Networks NIPS 2018 Sequential Person Recognition in Photo Albums With a Recurrent Network CVPR 2017 Attend in Groups: A Weakly-Supervised Deep Learning Framework for Learning From Web Data CVPR 2017 Towards Context-Aware Interaction Recognition for Visual Relationship Detection ICCV 2017 Fast Training of Triplet-Based Deep Binary Embedding Networks CVPR 2016