{"total":33,"rows":[{"id":"2405.11582","title":"SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization","created":"2024-05-19","cited_by_count":17,"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":"2502.13178","title":"Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2505.02309","title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","created":"2025-05-05","cited_by_count":9,"area":null},{"id":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","cited_by_count":5,"area":null},{"id":"2406.19301","title":"MCNC: Manifold-Constrained Reparameterization for Neural Compression","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2409.17020","title":"PTQ4RIS: Post-Training Quantization for Referring Image Segmentation","created":"2024-09-25","cited_by_count":4,"area":null},{"id":"2511.22334","title":"Edge Deployment of Small Language Models, a comprehensive comparison of CPU, GPU and NPU backends","created":"2025-11-27","cited_by_count":4,"area":null},{"id":"2601.11667","title":"Distill-then-Replace: Efficient Task-Specific Hybrid Attention Model Construction","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2406.03478","title":"Convolutional Neural Networks and Vision Transformers for Fashion MNIST Classification: A Literature Review","created":"2024-06-05","cited_by_count":2,"area":null},{"id":"2410.10849","title":"Continuous Approximations for Improving Quantization Aware Training of LLMs","created":"2024-10-06","cited_by_count":2,"area":null},{"id":"2412.12883","title":"A Comparative Study of Pruning Methods in Transformer-based Time Series Forecasting","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2507.21573","title":"LinDeps: A Fine-tuning Free Post-Pruning Method to Remove Layer-Wise Linear Dependencies with Guaranteed Performance Preservation","created":"2025-07-29","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":"2602.15200","title":"COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2608.30505","title":"Tensor Methods for Language Models: From Token Representation to Training, Adaptation, Inference, Compression, and Interpretability","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2504.03749","title":"Input Resolution Downsizing as a Compression Technique for Vision Deep Learning Systems","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2504.08620","title":"Efficient Mixture of Geographical Species for On Device Wildlife Monitoring","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2505.00350","title":"Optimizing Deep Neural Networks using Safety-Guided Self Compression","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2506.05641","title":"Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2506.07695","title":"Towards a Small Language Model Lifecycle Framework","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2507.17245","title":"DistrAttention: An Efficient and Flexible Self-Attention Mechanism on Modern GPUs","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2508.08514","title":"DeCAL Tokenwise Compression","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2509.00914","title":"TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2509.10199","title":"Beyond Token Limits: Assessing Language Model Performance on Long Text Classification","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2511.14111","title":"CascadedViT: Cascaded Chunk-FeedForward and Cascaded Group Attention Vision Transformer","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.09530","title":"Transformers for Tabular Data: A Training Perspective of Self-Attention via Optimal Transport","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2512.14090","title":"Arithmetic-Intensity-Aware Quantization","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.06252","title":"D-Legion: A Scalable Many-Core Architecture for Accelerating Matrix Multiplication in Quantized LLMs","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2604.17286","title":"Depth Adaptive Efficient Visual Autoregressive Modeling","created":"2026-04-19","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":"2608.20988","title":"Jacobian-guided Noise Injection for Quantization Robustness in Large Language Models","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.24973","title":"Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}