{"total":38,"rows":[{"id":"2309.10668","title":"Language Modeling Is Compression","created":"2023-09-19","cited_by_count":225,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2401.17139","title":"Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models","created":"2024-01-30","cited_by_count":35,"area":null},{"id":"2404.03626","title":"Training LLMs over Neurally Compressed Text","created":"2024-04-04","cited_by_count":17,"area":null},{"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":"2407.18995","title":"SWIFT: Semantic Watermarking for Image Forgery Thwarting","created":"2024-07-26","cited_by_count":8,"area":null},{"id":"2410.14086","title":"In-context learning and Occam's razor","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2402.17759","title":"Towards Optimal Learning of Language Models","created":"2024-02-27","cited_by_count":7,"area":null},{"id":"2409.15046","title":"AlphaZip: Neural Network-Enhanced Lossless Text Compression","created":"2024-09-23","cited_by_count":7,"area":null},{"id":"2508.15390","title":"Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training","created":"2025-08-21","cited_by_count":7,"area":null},{"id":"2508.01782","title":"Joint Lossless Compression and Steganography for Medical Images via Large Language Models","created":"2025-08-03","cited_by_count":6,"area":null},{"id":"2402.00861","title":"Evaluating Large Language Models for Generalization and Robustness via Data Compression","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2402.03471","title":"The Information of Large Language Model Geometry","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2503.13992","title":"The KoLMogorov Test: Compression by Code Generation","created":"2025-03-18","cited_by_count":5,"area":null},{"id":"2411.13033","title":"LMM-driven Semantic Image-Text Coding for Ultra Low-bitrate Learned Image Compression","created":"2024-11-20","cited_by_count":4,"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":"2509.24373","title":"Prediction-Powered Communication with Distortion Guarantees","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2410.10672","title":"Large Language Model Evaluation via Matrix Nuclear-Norm","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2412.15250","title":"An Enhanced Text Compression Approach Using Transformer-based Language Models","created":"2024-12-15","cited_by_count":2,"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":"2601.02875","title":"Revisiting Data Compression with Language Modeling","created":"2026-01-06","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":"2407.01017","title":"Coding for Intelligence from the Perspective of Category","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2510.22207","title":"The Lossy Horizon: Error-Bounded Predictive Coding for Lossy Text Compression (Episode I)","created":"2025-10-25","cited_by_count":1,"area":null},{"id":"2510.23035","title":"A high-capacity linguistic steganography based on entropy-driven rank-token mapping","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2601.10267","title":"In-Context Source and Channel Coding","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2602.13194","title":"Semantic Chunking and the Entropy of Natural Language","created":"2026-02-13","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":"2501.07641","title":"GPT as a Monte Carlo Language Tree: A Probabilistic Perspective","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2510.10300","title":"The Algorithmic Regulator","created":"2025-10-11","cited_by_count":0,"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":"2603.04272","title":"SSR: A Generic Framework for Text-Aided Map Compression for Localization","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2605.01991","title":"Real-Time Text Transmission via LLM-Based Entropy Coding over Fixed-Rate Channels","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2608.16438","title":"The Value of a Prompt: An LLM-Relative Kolmogorov-Complexity Approach","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.21309","title":"An Introduction to Compression-Based Machine Learning","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.39623","title":"Semantic Watermarking for Malicious Image Manipulation Detection","created":"2026-09-30","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}