{"total":15,"rows":[{"id":"2410.05078","title":"Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2602.09821","title":"Text summarization via global structure awareness","created":"2026-02-10","cited_by_count":12,"area":null},{"id":"2511.08066","title":"Information Capacity: Evaluating the Efficiency of Large Language Models via Text Compression","created":"2025-11-11","cited_by_count":7,"area":null},{"id":"2602.19626","title":"Nacrith: Neural Lossless Compression via Ensemble Context Modeling and High-Precision CDF Coding","created":"2026-02-23","cited_by_count":4,"area":null},{"id":"2511.10660","title":"Test-Time Steering for Lossless Text Compression via Weighted Product of Experts","created":"2025-11-04","cited_by_count":3,"area":null},{"id":"2505.16256","title":"DualComp: End-to-End Learning of a Unified Dual-Modality Lossless Compressor","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2602.22286","title":"OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2601.10267","title":"In-Context Source and Channel Coding","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2607.24192","title":"LLM-based Source Code Compression via Thresholded Symbol Ranking","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2608.12218","title":"Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2601.17684","title":"A Model-Driven Lossless Compression Algorithm Resistant to Mismatch","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2603.08771","title":"Micro-Diffusion Compression - Binary Tree Tweedie Denoising for Online Probability Estimation","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2608.11249","title":"Diffuse to Compress: Leveraging Diffusion LMs for Lossless Compression","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.06008","title":"Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2610.10738","title":"Lossy Compressive Text Autoencoders","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}