Zhikai Li

最新

• MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction
• RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers
• Patch Similarity Aware Data-Free Quantization for Vision Transformers
• Patch-Wise Mixed-Precision Quantization of Vision Transformer
• DCIFPN: Deformable cross-scale interaction feature pyramid network for object detection
• Region Probability Map-Guided Fast Wide-Area Multiobject Detection
• Mechanical Particle Filter Based Active Vision System for Fast Wide-Area Multi-Object Detection
• Sparsity Induction for Accurate Post-Training Pruning of Large Language Models
• SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model
• DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation
• LLM Inference Unveiled: Survey and Roofline Model Insights
• Qft: Quantized full-parameter tuning of llms with affordable resources
• PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers
• BinaryViT: Towards Efficient and Accurate Binary Vision Transformers
• Rethinking Prediction Alignment in One-stage Object Detection
• Dual-Discriminator Adversarial Framework for Data-Free Quantization
• Hardware-Oriented Algorithm for High-Speed Laser Centerline Extraction Based on Hessian Matrix
• K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge
• PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models
• Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval
• CacheQuant: Comprehensively Accelerated Diffusion Models
• K-sort arena: Efficient and reliable benchmarking for generative models via k-wise human preferences
• DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation
• RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization
• EDA-DM: Enhanced distribution alignment for post-training quantization of diffusion models
• I-ViT: Integer-only Quantization for Efficient Vision Transformer Inference