Mingbao Lin

papers

1,872

total citations

papers (22)

IntraQ: Learning Synthetic Images With Intra-Class Heterogeneity for Zero-Shot Network Quantization

CVPR 2022arXiv

citations

Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference

AAAI 2025arXiv

citations

DiffRate : Differentiable Compression Rate for Efficient Vision Transformers

ICCV 2023arXiv

citations

CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models

NEURIPS 2025arXiv

citations

Knowledge Condensation Distillation

ECCV 2022arXiv

citations

ARM: Any-Time Super-Resolution Method

ECCV 2022arXiv

citations

Q-DETR: An Efficient Low-Bit Quantized Detection Transformer

CVPR 2023arXiv

citations

Dynamic Dual Trainable Bounds for Ultra-Low Precision Super-Resolution Networks

ECCV 2022arXiv

citations

AccDiffusion: An Accurate Method for Higher-Resolution Image Generation

ECCV 2024arXiv

citations

Bi-ViT: Pushing the Limit of Vision Transformer Quantization

AAAI 2024arXiv

citations

Fine-Grained Data Distribution Alignment for Post-Training Quantization

ECCV 2022arXiv

citations

SMMix: Self-Motivated Image Mixing for Vision Transformers

ICCV 2023arXiv

citations

Discriminator-Cooperated Feature Map Distillation for GAN Compression

CVPR 2023arXiv

citations

Representation Disparity-aware Distillation for 3D Object Detection

ICCV 2023arXiv

citations

UniPTS: A Unified Framework for Proficient Post-Training Sparsity

CVPR 2024arXiv

citations

Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing

AAAI 2025arXiv

citations

Learning Best Combination for Efficient N:M Sparsity

NEURIPS 2022

citations

Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement

ICML 2024

citations

Mingbao Lin

papers (22)

HRank: Filter Pruning Using High-Rank Feature Map

SeqTR: A Simple Yet Universal Network for Visual Grounding

Rotated Binary Neural Network

ReCU: Reviving the Dead Weights in Binary Neural Networks

IntraQ: Learning Synthetic Images With Intra-Class Heterogeneity for Zero-Shot Network Quantization

Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference

DiffRate : Differentiable Compression Rate for Efficient Vision Transformers

CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models

Knowledge Condensation Distillation

ARM: Any-Time Super-Resolution Method

Q-DETR: An Efficient Low-Bit Quantized Detection Transformer

Dynamic Dual Trainable Bounds for Ultra-Low Precision Super-Resolution Networks

AccDiffusion: An Accurate Method for Higher-Resolution Image Generation

Bi-ViT: Pushing the Limit of Vision Transformer Quantization

Fine-Grained Data Distribution Alignment for Post-Training Quantization

SMMix: Self-Motivated Image Mixing for Vision Transformers

Discriminator-Cooperated Feature Map Distillation for GAN Compression

Representation Disparity-aware Distillation for 3D Object Detection

UniPTS: A Unified Framework for Proficient Post-Training Sparsity

Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing

Learning Best Combination for Efficient N:M Sparsity

Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement

papers (22)

HRank: Filter Pruning Using High-Rank Feature Map

SeqTR: A Simple Yet Universal Network for Visual Grounding

Rotated Binary Neural Network

ReCU: Reviving the Dead Weights in Binary Neural Networks

IntraQ: Learning Synthetic Images With Intra-Class Heterogeneity for Zero-Shot Network Quantization

Boosting Multimodal Large Language Models with Visual Tokens Withdrawal for Rapid Inference

DiffRate : Differentiable Compression Rate for Efficient Vision Transformers

CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models

Knowledge Condensation Distillation

ARM: Any-Time Super-Resolution Method

Q-DETR: An Efficient Low-Bit Quantized Detection Transformer

Dynamic Dual Trainable Bounds for Ultra-Low Precision Super-Resolution Networks

AccDiffusion: An Accurate Method for Higher-Resolution Image Generation

Bi-ViT: Pushing the Limit of Vision Transformer Quantization

Fine-Grained Data Distribution Alignment for Post-Training Quantization

SMMix: Self-Motivated Image Mixing for Vision Transformers

Discriminator-Cooperated Feature Map Distillation for GAN Compression

Representation Disparity-aware Distillation for 3D Object Detection

UniPTS: A Unified Framework for Proficient Post-Training Sparsity

Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing

Learning Best Combination for Efficient N:M Sparsity

Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement