{"total":22,"rows":[{"id":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195,"area":null},{"id":"2307.00526","title":"TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition","created":"2023-07-02","cited_by_count":17,"area":null},{"id":"2211.09718","title":"Numerical Optimizations for Weighted Low-rank Estimation on Language Model","created":"2022-11-02","cited_by_count":14,"area":null},{"id":"2208.13363","title":"Survey: Exploiting Data Redundancy for Optimization of Deep Learning","created":"2022-08-29","cited_by_count":6,"area":null},{"id":"2102.07071","title":"Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices","created":"2021-02-14","cited_by_count":5,"area":null},{"id":"2210.15379","title":"MorphTE: Injecting Morphology in Tensorized Embeddings","created":"2022-10-27","cited_by_count":5,"area":null},{"id":"2306.00342","title":"Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2403.00625","title":"Bias Mitigation in Fine-tuning Pre-trained Models for Enhanced Fairness and Efficiency","created":"2024-03-01","cited_by_count":3,"area":null},{"id":"2408.11868","title":"Improving embedding with contrastive fine-tuning on small datasets with expert-augmented scores","created":"2024-08-19","cited_by_count":3,"area":null},{"id":"2506.02818","title":"ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2205.01954","title":"Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem","created":"2022-05-04","cited_by_count":1,"area":null},{"id":"2405.15877","title":"Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2412.10856","title":"RWKV-edge: Deeply Compressed RWKV for Resource-Constrained Devices","created":"2024-12-14","cited_by_count":1,"area":null},{"id":"2507.03828","title":"IMPACT: Importance-Aware Activation Space Reconstruction","created":"2025-07-04","cited_by_count":1,"area":null},{"id":"2102.01345","title":"Fast Exploration of Weight Sharing Opportunities for CNN Compression","created":"2021-02-02","cited_by_count":0,"area":null},{"id":"2211.12715","title":"Embedding Compression for Text Classification Using Dictionary Screening","created":"2022-11-23","cited_by_count":0,"area":null},{"id":"2505.24469","title":"Smooth Model Compression without Fine-Tuning","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2506.05617","title":"LFA applied to CNNs: Efficient Singular Value Decomposition of Convolutional Mappings by Local Fourier Analysis","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2506.13514","title":"TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2508.00220","title":"Semantic Compression for Word and Sentence Embeddings using Discrete Wavelet Transform","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2604.23375","title":"Hierarchical Spatio-Channel Clustering for Efficient Model Compression in Medical Image Analysis","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2606.08184","title":"TextEconomizer: Enhancing Lossy Text Compression with Denoising Transformers and Entropy Coding","created":"2026-06-06","cited_by_count":0,"area":null}],"next_cursor":null}