Mingbao Lin

Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling AAAI 2026 Progressive Supernet Training for Efficient Visual Autoregressive Modeling CVPR 2026 Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning ACL 2026 Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models EMNLP 2025 Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference AAAI 2025 CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences ICLR 2025 EasyInv: Toward Fast and Better DDIM Inversion ICML 2025 Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing AAAI 2025 AccDiffusion: An Accurate Method for Higher-Resolution Image Generation ECCV 2024 Bi-ViT: Pushing the Limit of Vision Transformer Quantization AAAI 2024 Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs ICLR 2024 Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement ICML 2024 LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement EMNLP 2024 UniPTS: A Unified Framework for Proficient Post-Training Sparsity CVPR 2024 Bi-directional Masks for Efficient N:M Sparse Training ICML 2023 CF-ViT: A General Coarse-to-Fine Method for Vision Transformer AAAI 2023 DiffRate : Differentiable Compression Rate for Efficient Vision Transformers ICCV 2023 Discriminator-Cooperated Feature Map Distillation for GAN Compression CVPR 2023 End-to-End Zero-Shot HOI Detection via Vision and Language Knowledge Distillation AAAI 2023 Q-DETR: An Efficient Low-Bit Quantized Detection Transformer CVPR 2023 Real-Time Image Demoir$\acute{e}$ing on Mobile Devices ICLR 2023 Representation Disparity-aware Distillation for 3D Object Detection ICCV 2023 Resilient Binary Neural Network AAAI 2023 SMMix: Self-Motivated Image Mixing for Vision Transformers ICCV 2023 ARM: Any-Time Super-Resolution Method ECCV 2022 Dynamic Dual Trainable Bounds for Ultra-Low Precision Super-Resolution Networks ECCV 2022 Fine-Grained Data Distribution Alignment for Post-Training Quantization ECCV 2022 IntraQ: Learning Synthetic Images With Intra-Class Heterogeneity for Zero-Shot Network Quantization CVPR 2022 Knowledge Condensation Distillation ECCV 2022 Learning Best Combination for Efficient N:M Sparsity NeurIPS 2022 SeqTR: A Simple Yet Universal Network for Visual Grounding ECCV 2022 ReCU: Reviving the Dead Weights in Binary Neural Networks ICCV 2021 Channel Pruning via Automatic Structure Search IJCAI 2020 HRank: Filter Pruning Using High-Rank Feature Map CVPR 2020 Rotated Binary Neural Network NeurIPS 2020 Towards Optimal Discrete Online Hashing with Balanced Similarity AAAI 2019