{"total":80,"rows":[{"id":"2212.08254","title":"RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformers","created":"2022-12-16","cited_by_count":137,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2302.02210","title":"Oscillation-free Quantization for Low-bit Vision Transformers","created":"2023-02-04","cited_by_count":57,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2209.05687","title":"PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision Transformers","created":"2022-09-13","cited_by_count":42,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","cited_by_count":28,"area":null},{"id":"2411.13918","title":"Quantization without Tears","created":"2024-11-21","cited_by_count":25,"area":null},{"id":"2405.17849","title":"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models","created":"2024-05-28","cited_by_count":23,"area":null},{"id":"2407.06794","title":"Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction","created":"2024-07-09","cited_by_count":23,"area":null},{"id":"2311.10126","title":"I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization","created":"2023-11-16","cited_by_count":19,"area":null},{"id":"2408.03291","title":"DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers","created":"2024-08-06","cited_by_count":19,"area":null},{"id":"2506.11543","title":"FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation","created":"2025-06-13","cited_by_count":19,"area":null},{"id":"2304.03986","title":"SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers","created":"2023-04-08","cited_by_count":18,"area":null},{"id":"2308.10814","title":"Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers","created":"2023-08-21","cited_by_count":18,"area":null},{"id":"2307.00331","title":"Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision","created":"2023-07-01","cited_by_count":17,"area":null},{"id":"2407.05266","title":"CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs","created":"2024-07-07","cited_by_count":17,"area":null},{"id":"2402.15490","title":"A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends","created":"2024-02-23","cited_by_count":16,"area":null},{"id":"2408.14468","title":"K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences","created":"2024-08-26","cited_by_count":16,"area":null},{"id":"2405.00314","title":"Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2511.06767","title":"QUARK: Quantization-Enabled Circuit Sharing for Transformer Acceleration by Exploiting Common Patterns in Nonlinear Operations","created":"2025-11-10","cited_by_count":11,"area":null},{"id":"2310.07147","title":"QFT: Quantized Full-parameter Tuning of LLMs with Affordable Resources","created":"2023-10-11","cited_by_count":10,"area":null},{"id":"2402.05628","title":"RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization","created":"2024-02-08","cited_by_count":10,"area":null},{"id":"2407.20021","title":"MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity","created":"2024-07-29","cited_by_count":9,"area":null},{"id":"2307.12659","title":"A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization","created":"2023-07-24","cited_by_count":8,"area":null},{"id":"2401.11243","title":"LRP-QViT: Mixed-Precision Vision Transformer Quantization via Layer-wise Relevance Propagation","created":"2024-01-20","cited_by_count":8,"area":null},{"id":"2406.18051","title":"ViT-1.58b: Mobile Vision Transformers in the 1-bit Era","created":"2024-06-26","cited_by_count":8,"area":null},{"id":"2407.09527","title":"BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networks","created":"2024-06-24","cited_by_count":8,"area":null},{"id":"2407.11041","title":"Integer-only Quantized Transformers for Embedded FPGA-based Time-series Forecasting in AIoT","created":"2024-07-06","cited_by_count":6,"area":null},{"id":"2409.15298","title":"Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model","created":"2024-09-04","cited_by_count":6,"area":null},{"id":"2412.04786","title":"Slicing Vision Transformer for Flexible Inference","created":"2024-12-06","cited_by_count":6,"area":null},{"id":"2405.19915","title":"P$^2$-ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision Transformer","created":"2024-05-30","cited_by_count":4,"area":null},{"id":"2409.00297","title":"On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic","created":"2024-08-30","cited_by_count":4,"area":null},{"id":"2410.01813","title":"Privacy-Preserving SAM Quantization for Efficient Edge Intelligence in Healthcare","created":"2024-09-14","cited_by_count":4,"area":null},{"id":"2502.11895","title":"Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2601.21238","title":"PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2405.03882","title":"Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2407.18437","title":"Mixed Non-linear Quantization for Vision Transformers","created":"2024-07-26","cited_by_count":3,"area":null},{"id":"2410.09113","title":"M$^2$-ViT: Accelerating Hybrid Vision Transformers with Two-Level Mixed Quantization","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2411.03697","title":"TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture","created":"2024-11-06","cited_by_count":3,"area":null},{"id":"2412.16553","title":"Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2503.03088","title":"AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2503.06515","title":"SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2511.00812","title":"LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2511.21513","title":"IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2407.12070","title":"Co-Designing Binarized Transformer and Hardware Accelerator for Efficient End-to-End Edge Deployment","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2502.15488","title":"FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2505.02314","title":"NeuroSim V1.5: Improved Software Backbone for Benchmarking Compute-in-Memory Accelerators with Device and Circuit-level Non-idealities","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2508.07710","title":"Training-Free ANN-to-SNN Conversion for High-Performance Spiking Transformer","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2602.08224","title":"Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2605.04738","title":"OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization","created":"2026-05-06","cited_by_count":2,"area":null},{"id":"2211.09643","title":"CPT-V: A Contrastive Approach to Post-Training Quantization of Vision Transformers","created":"2022-11-17","cited_by_count":1,"area":null},{"id":"2403.07339","title":"IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2405.01775","title":"Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2411.05882","title":"When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization","created":"2024-11-08","cited_by_count":1,"area":null},{"id":"2501.12087","title":"UAV-Assisted Real-Time Disaster Detection Using Optimized Transformer Model","created":"2025-01-21","cited_by_count":1,"area":null},{"id":"2502.09125","title":"Enhanced Structured Lasso Pruning with Class-wise Information","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2509.10334","title":"I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2511.15369","title":"IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2305.19365","title":"Vision Transformers for Mobile Applications: A Short Survey","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2404.00949","title":"Harnessing The Power of Attention For Patch-Based Biomedical Image Classification","created":"2024-04-01","cited_by_count":0,"area":null},{"id":"2408.08437","title":"PQV-Mobile: A Combined Pruning and Quantization Toolkit to Optimize Vision Transformers for Mobile Applications","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2411.14733","title":"FLARE: FP-Less PTQ and Low-ENOB ADC Based AMS-PiM for Error-Resilient, Fast, and Efficient Transformer Acceleration","created":"2024-11-22","cited_by_count":0,"area":null},{"id":"2411.17720","title":"MAS-Attention: Memory-Aware Stream Processing for Attention Acceleration on Resource-Constrained Edge Devices","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2504.18547","title":"Low-Bit Integerization of Vision Transformers using Operand Reordering for Efficient Hardware","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2511.09347","title":"FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2604.25306","title":"QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.01742","title":"Joint Architecture-Token-Bitwidth Multi-Axis Optimization of Vision Transformers for Semiconductor IC Packaging","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.21171","title":"FTerViT: Fully Ternary Vision Transformer","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2607.15421","title":"qZACH-ViT: Quantization-Aware Intrinsic Explanations with Recursive Attribution-Stabilized Optimization","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.24981","title":"Enabling Fully Integer-Only Inference for Lightweight Detection Transformers","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2607.28589","title":"MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.01343","title":"DeVIT: Low-Power Vision Transformer Acceleration Using Delta Computation","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.16756","title":"Binarized High-Efficiency RAW Video Restoration and Beyond","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.24469","title":"Low-Rank Ternary Adaptation for Fine-Tuning Transformers","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.29667","title":"A Target-Centric Survey of Quantization-Aware Training","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.13947","title":"Hardware-Aware Learned Representation Compression for Distributed In-Sensor Vision","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.33586","title":"Approximating Softmax in Pretrained LLMs: Model Sensitivity and Kernel Acceleration","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.16298","title":"Memory-Efficient Integer-Only Training of Deep Neural Networks","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}