{"total":25,"rows":[{"id":"2402.15319","title":"GPTVQ: The Blessing of Dimensionality for LLM Quantization","created":"2024-02-23","cited_by_count":82,"area":null},{"id":"2310.01382","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","created":"2023-10-02","cited_by_count":62,"area":null},{"id":"2303.00633","title":"An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization","created":"2023-03-01","cited_by_count":25,"area":null},{"id":"2405.13796","title":"Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling","created":"2024-05-22","cited_by_count":23,"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":"2109.04186","title":"Fine-grained Data Distribution Alignment for Post-Training Quantization","created":"2021-09-09","cited_by_count":9,"area":null},{"id":"2202.10100","title":"Enabling On-Device Smartphone GPU based Training: Lessons Learned","created":"2022-02-21","cited_by_count":4,"area":null},{"id":"2203.03794","title":"YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers","created":"2022-03-08","cited_by_count":4,"area":null},{"id":"2210.09188","title":"Sub-8-bit quantization for on-device speech recognition: a regularization-free approach","created":"2022-10-17","cited_by_count":4,"area":null},{"id":"2212.12653","title":"Hyperspherical Quantization: Toward Smaller and More Accurate Models","created":"2022-12-24","cited_by_count":4,"area":null},{"id":"2207.11048","title":"Quantized Sparse Weight Decomposition for Neural Network Compression","created":"2022-07-22","cited_by_count":3,"area":null},{"id":"2209.04966","title":"Multi-modal Streaming 3D Object Detection","created":"2022-09-12","cited_by_count":3,"area":null},{"id":"2608.04048","title":"Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs","created":"2026-08-04","cited_by_count":3,"area":null},{"id":"2207.01260","title":"CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2211.11397","title":"Learning Low-Rank Representations for Model Compression","created":"2022-11-21","cited_by_count":2,"area":null},{"id":"2412.10261","title":"MVQ:Towards Efficient DNN Compression and Acceleration with Masked Vector Quantization","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2603.06606","title":"LegoNet: Memory Footprint Reduction Through Block Weight Clustering","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2107.10998","title":"Pruning Ternary Quantization","created":"2021-07-23","cited_by_count":0,"area":null},{"id":"2111.10320","title":"Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression","created":"2021-11-19","cited_by_count":0,"area":null},{"id":"2210.05111","title":"Deep learning model compression using network sensitivity and gradients","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2212.12649","title":"Hyperspherical Loss-Aware Ternary Quantization","created":"2022-12-24","cited_by_count":0,"area":null},{"id":"2403.19163","title":"D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representations","created":"2024-03-28","cited_by_count":0,"area":null},{"id":"2501.03095","title":"A Novel Structure-Agnostic Multi-Objective Approach for Weight-Sharing Compression in Deep Neural Networks","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2503.08668","title":"SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2504.00395","title":"A Theory of Machine Understanding via the Minimum Description Length Principle","created":"2025-04-01","cited_by_count":0,"area":null}],"next_cursor":null}