{"total":108,"rows":[{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414,"area":null},{"id":"2405.10739","title":"Efficient Multimodal Large Language Models: A Survey","created":"2024-05-17","cited_by_count":96,"area":"mllm"},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2310.08041","title":"QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models","created":"2023-10-12","cited_by_count":64,"area":null},{"id":"2304.09145","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","created":"2023-04-18","cited_by_count":61,"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":"2501.17116","title":"Optimizing Large Language Model Training Using FP4 Quantization","created":"2025-01-28","cited_by_count":56,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2307.16867","title":"Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy","created":"2023-07-31","cited_by_count":44,"area":null},{"id":"2312.07950","title":"CBQ: Cross-Block Quantization for Large Language Models","created":"2023-12-13","cited_by_count":34,"area":null},{"id":"2312.13789","title":"TinySAM: Pushing the Envelope for Efficient Segment Anything Model","created":"2023-12-21","cited_by_count":33,"area":"distill"},{"id":"2407.12951","title":"AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer","created":"2024-07-17","cited_by_count":29,"area":null},{"id":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","cited_by_count":28,"area":null},{"id":"2302.06586","title":"Stitchable Neural Networks","created":"2023-02-13","cited_by_count":26,"area":null},{"id":"2411.13918","title":"Quantization without Tears","created":"2024-11-21","cited_by_count":25,"area":null},{"id":"2304.00253","title":"Q-DETR: An Efficient Low-Bit Quantized Detection Transformer","created":"2023-04-01","cited_by_count":24,"area":null},{"id":"2503.02891","title":"Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies","created":"2025-02-26","cited_by_count":24,"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":"2504.02508","title":"APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers","created":"2025-04-03","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":"2306.16678","title":"BinaryViT: Pushing Binary Vision Transformers Towards Convolutional Models","created":"2023-06-29","cited_by_count":17,"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":"2403.09192","title":"PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation","created":"2024-03-14","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":"2302.00956","title":"Resilient Binary Neural Network","created":"2023-02-02","cited_by_count":13,"area":null},{"id":"2304.05659","title":"RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer","created":"2023-04-12","cited_by_count":13,"area":null},{"id":"2305.12354","title":"Bi-ViT: Pushing the Limit of Vision Transformer Quantization","created":"2023-05-21","cited_by_count":13,"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":"2510.18091","title":"Accelerating Vision Transformers with Adaptive Patch Sizes","created":"2025-10-20","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":"2410.21759","title":"IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models","created":"2024-10-29","cited_by_count":10,"area":"diffusion"},{"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":"2501.06357","title":"Mix-QViT: Mixed-Precision Vision Transformer Quantization Driven by Layer Importance and Quantization Sensitivity","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2302.10494","title":"The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers","created":"2023-02-21","cited_by_count":8,"area":"distill"},{"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":"2506.11784","title":"GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers","created":"2025-06-13","cited_by_count":8,"area":null},{"id":"2305.14730","title":"BinaryViT: Towards Efficient and Accurate Binary Vision Transformers","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2402.07545","title":"TransAxx: Efficient Transformers with Approximate Computing","created":"2024-02-12","cited_by_count":7,"area":null},{"id":"2403.04908","title":"Self-Adapting Large Visual-Language Models to Edge Devices across Visual Modalities","created":"2024-03-07","cited_by_count":7,"area":"mllm"},{"id":"2409.17634","title":"P4Q: Learning to Prompt for Quantization in Visual-language Models","created":"2024-09-26","cited_by_count":7,"area":"mllm"},{"id":"2509.09955","title":"Adaptive Token Merging for Efficient Transformer Semantic Communication at the Edge","created":"2025-09-12","cited_by_count":7,"area":"inference"},{"id":"2407.10704","title":"Quantized Prompt for Efficient Generalization of Vision-Language Models","created":"2024-07-15","cited_by_count":6,"area":"mllm"},{"id":"2503.02394","title":"BHViT: Binarized Hybrid Vision Transformer","created":"2025-03-04","cited_by_count":5,"area":null},{"id":"2505.20932","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2305.07931","title":"GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples","created":"2023-05-13","cited_by_count":4,"area":null},{"id":"2407.18175","title":"Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2510.21879","title":"TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary Weights and Distilled Knowledge","created":"2025-10-23","cited_by_count":4,"area":"mllm"},{"id":"2404.06773","title":"Adapting LLaMA Decoder to Vision Transformer","created":"2024-04-10","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":"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":"2501.05904","title":"Binary Event-Driven Spiking Transformer","created":"2025-01-10","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":"2505.18608","title":"Spiking Neural Networks Need High Frequency Information","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2507.19131","title":"MixA-Q: Revisiting Activation Sparsity for Vision Transformers from a Mixed-Precision Quantization Perspective","created":"2025-07-25","cited_by_count":3,"area":null},{"id":"2509.21173","title":"Less Precise Can Be More Reliable: A Systematic Evaluation of Quantization's Impact on VLMs Beyond Accuracy","created":"2025-09-25","cited_by_count":3,"area":"mllm"},{"id":"2305.12796","title":"Spatiotemporal Attention-based Semantic Compression for Real-time Video Recognition","created":"2023-05-22","cited_by_count":2,"area":null},{"id":"2403.06497","title":"QuantTune: Optimizing Model Quantization with Adaptive Outlier-Driven Fine Tuning","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2404.00672","title":"A General and Efficient Training for Transformer via Token Expansion","created":"2024-03-31","cited_by_count":2,"area":null},{"id":"2507.14481","title":"DFQ-ViT: Data-Free Quantization for Vision Transformers without Fine-tuning","created":"2025-07-19","cited_by_count":2,"area":null},{"id":"2507.17768","title":"Enhancing Quantization-Aware Training on Edge Devices via Relative Entropy Coreset Selection and Cascaded Layer Correction","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2507.22349","title":"MSQ: Memory-Efficient Bit Sparsification Quantization","created":"2025-07-30","cited_by_count":2,"area":null},{"id":"2511.10004","title":"LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformers","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2603.19873","title":"SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2303.01166","title":"BPT: Binary Point Cloud Transformer for Place Recognition","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2402.13497","title":"In-Distribution Consistency Regularization Improves the Generalization of Quantization-Aware Training","created":"2024-02-21","cited_by_count":1,"area":"distill"},{"id":"2403.09998","title":"FBPT: A Fully Binary Point Transformer","created":"2024-03-15","cited_by_count":1,"area":null},{"id":"2408.08250","title":"Computer Vision Model Compression Techniques for Embedded Systems: A Survey","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2412.11186","title":"Efficient Quantization-Aware Training on Segment Anything Model in Medical Images and Its Deployment","created":"2024-12-15","cited_by_count":1,"area":null},{"id":"2506.10831","title":"Efficiency Robustness of Dynamic Deep Learning Systems","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2508.10370","title":"eMamba: Efficient Acceleration Framework for Mamba Models in Edge Computing","created":"2025-08-14","cited_by_count":1,"area":"ssm"},{"id":"2508.10557","title":"PTQAT: A Hybrid Parameter-Efficient Quantization Algorithm for 3D Perception Tasks","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2508.16311","title":"Exploiting Information Redundancy in Attention Maps for Extreme Quantization of Vision Transformers","created":"2025-08-22","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":"2602.18861","title":"Joint Post-Training Quantization of Vision Transformers with Learned Prompt-Guided Data Generation","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2603.09582","title":"BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers","created":"2026-03-10","cited_by_count":1,"area":"diffusion"},{"id":"2604.04523","title":"LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2605.01330","title":"Colinearity Decay: Training Quantization-Friendly ViTs with Outlier Decay","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2605.16423","title":"Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.29259","title":"KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2306.15390","title":"DCP-NAS: Discrepant Child-Parent Neural Architecture Search for 1-bit CNNs","created":"2023-06-27","cited_by_count":0,"area":null},{"id":"2401.11652","title":"OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning","created":"2024-01-22","cited_by_count":0,"area":null},{"id":"2402.01169","title":"Faster Inference of Integer SWIN Transformer by Removing the GELU Activation","created":"2024-02-02","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":"2504.03118","title":"NuWa: Deriving Lightweight Class-Specific Vision Transformers for Edge Devices","created":"2025-04-04","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":"2506.09066","title":"ReStNet: A Reusable & Stitchable Network for Dynamic Adaptation on IoT Devices","created":"2025-06-08","cited_by_count":0,"area":null},{"id":"2507.02222","title":"High-Fidelity Differential-information Driven Binary Vision Transformer","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2507.12780","title":"Compact Vision Transformer by Reduction of Kernel Complexity","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2509.15514","title":"MEC-Quant: Maximum Entropy Coding for Extremely Low Bit Quantization-Aware Training","created":"2025-09-19","cited_by_count":0,"area":"moe"},{"id":"2510.18650","title":"Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2511.23166","title":"Energy-Efficient Vision Transformer Inference for Edge-AI Deployment","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2603.06746","title":"ButterflyViT: 354$\\times$ Expert Compression for Edge Vision Transformers","created":"2026-03-06","cited_by_count":0,"area":"moe"},{"id":"2605.07317","title":"Amortized-Precision Quantization for Early-Exit Vision Transformers","created":"2026-05-08","cited_by_count":0,"area":"inference"},{"id":"2605.21171","title":"FTerViT: Fully Ternary Vision Transformer","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.26415","title":"The Rescue Effect: Spatio-Semantic Early Exit Bypasses Quantization Collapse in CLIP","created":"2026-05-26","cited_by_count":0,"area":"mllm"},{"id":"2607.11211","title":"FastTPS: An Optimized Method for LLM Token Phase for AI accelerators","created":"2026-07-13","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}],"next_cursor":"100"}