Mingbao Lin

22

Papers

81

Total Citations

Papers (22)

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

NeurIPS 2025arXiv

AccDiffusion: An Accurate Method for Higher-Resolution Image Generation

UniPTS: A Unified Framework for Proficient Post-Training Sparsity

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

HRank: Filter Pruning Using High-Rank Feature Map

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

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

Discriminator-Cooperated Feature Map Distillation for GAN Compression

Representation Disparity-aware Distillation for 3D Object Detection

DiffRate : Differentiable Compression Rate for Efficient Vision Transformers

SMMix: Self-Motivated Image Mixing for Vision Transformers

Knowledge Condensation Distillation

Fine-Grained Data Distribution Alignment for Post-Training Quantization

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

ARM: Any-Time Super-Resolution Method

SeqTR: A Simple Yet Universal Network for Visual Grounding

ReCU: Reviving the Dead Weights in Binary Neural Networks

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

Bi-ViT: Pushing the Limit of Vision Transformer Quantization

Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement

Rotated Binary Neural Network

Learning Best Combination for Efficient N:M Sparsity