{"total":17,"rows":[{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"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":"2401.01543","title":"Retraining-free Model Quantization via One-Shot Weight-Coupling Learning","created":"2024-01-03","cited_by_count":13,"area":null},{"id":"2403.07564","title":"RSBuilding: Towards General Remote Sensing Image Building Extraction and Change Detection with Foundation Model","created":"2024-03-12","cited_by_count":12,"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":"2404.18311","title":"Towards Incremental Learning in Large Language Models: A Critical Review","created":"2024-04-28","cited_by_count":6,"area":null},{"id":"2307.04816","title":"Q-YOLO: Efficient Inference for Real-time Object Detection","created":"2023-07-01","cited_by_count":3,"area":null},{"id":"2308.14938","title":"Entropy-based Guidance of Deep Neural Networks for Accelerated Convergence and Improved Performance","created":"2023-08-28","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":"2404.00672","title":"A General and Efficient Training for Transformer via Token Expansion","created":"2024-03-31","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":"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":"2311.14114","title":"SONIQ: System-Optimized Noise-Injected Ultra-Low-Precision Quantization with Full-Precision Parity","created":"2023-11-23","cited_by_count":0,"area":null},{"id":"2511.05898","title":"Q$^2$: Quantization-Aware Gradient Balancing and Attention Alignment for Low-Bit Quantization","created":"2025-11-08","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":"2603.05964","title":"QATMA: Quantization-Aware Training with Multimodal Alignment for Open-Vocabulary Object Detection","created":"2026-03-06","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}],"next_cursor":null}