{"total":20,"rows":[{"id":"2205.12379","title":"Gaussian Pre-Activations in Neural Networks: Myth or Reality?","created":"2022-05-24","cited_by_count":9,"area":null},{"id":"2304.01016","title":"Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders","created":"2023-03-31","cited_by_count":5,"area":null},{"id":"2503.15748","title":"PARQ: Piecewise-Affine Regularized Quantization","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2103.02394","title":"Self-Distribution Binary Neural Networks","created":"2021-03-03","cited_by_count":4,"area":null},{"id":"2104.02233","title":"TENT: Efficient Quantization of Neural Networks on the tiny Edge with Tapered FixEd PoiNT","created":"2021-04-06","cited_by_count":4,"area":null},{"id":"2502.17941","title":"Optimal Brain Apoptosis","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2201.07634","title":"FAT: An In-Memory Accelerator with Fast Addition for Ternary Weight Neural Networks","created":"2022-01-19","cited_by_count":2,"area":null},{"id":"2110.02550","title":"CBP: Backpropagation with constraint on weight precision using a pseudo-Lagrange multiplier method","created":"2021-10-06","cited_by_count":1,"area":null},{"id":"2211.13838","title":"Signed Binary Weight Networks","created":"2022-11-25","cited_by_count":1,"area":null},{"id":"2302.14458","title":"Ultra-low Precision Multiplication-free Training for Deep Neural Networks","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2303.17612","title":"oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes","created":"2023-03-30","cited_by_count":1,"area":null},{"id":"2306.17266","title":"Subgraph Stationary Hardware-Software Inference Co-Design","created":"2023-06-21","cited_by_count":1,"area":null},{"id":"2602.06694","title":"NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2108.10101","title":"On the Acceleration of Deep Neural Network Inference using Quantized Compressed Sensing","created":"2021-08-23","cited_by_count":0,"area":null},{"id":"2210.02637","title":"IR2Net: Information Restriction and Information Recovery for Accurate Binary Neural Networks","created":"2022-10-06","cited_by_count":0,"area":null},{"id":"2312.01581","title":"PLUM: Improving Inference Efficiency By Leveraging Repetition-Sparsity Trade-Off","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2508.11112","title":"Quantization through Piecewise-Affine Regularization: Optimization and Statistical Guarantees","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2603.22770","title":"From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2603.25385","title":"GlowQ: Group-Shared LOw-Rank Approximation for Quantized LLMs","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2609.38521","title":"ShamAN-Q: Shampoo Augmented NanoQuant for Sub-1-bit LLM Weights","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}