{"total":173,"rows":[{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500,"area":null},{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311,"area":null},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163,"area":null},{"id":"2406.07548","title":"Image and Video Tokenization with Binary Spherical Quantization","created":"2024-06-11","cited_by_count":112,"area":null},{"id":"2402.04379","title":"Fine-Tuned Language Models Generate Stable Inorganic Materials as Text","created":"2024-02-06","cited_by_count":93,"area":null},{"id":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80,"area":null},{"id":"2310.06213","title":"GeoLLM: Extracting Geospatial Knowledge from Large Language Models","created":"2023-10-10","cited_by_count":64,"area":null},{"id":"2404.09937","title":"Compression Represents Intelligence Linearly","created":"2024-04-15","cited_by_count":56,"area":null},{"id":"2405.15471","title":"Emergence of a High-Dimensional Abstraction Phase in Language Transformers","created":"2024-05-24","cited_by_count":56,"area":null},{"id":"2312.17173","title":"Non-Vacuous Generalization Bounds for Large Language Models","created":"2023-12-28","cited_by_count":53,"area":null},{"id":"2406.06144","title":"Language Models Resist Alignment: Evidence From Data Compression","created":"2024-06-10","cited_by_count":53,"area":null},{"id":"2403.13799","title":"Reverse Training to Nurse the Reversal Curse","created":"2024-03-20","cited_by_count":49,"area":null},{"id":"2310.20501","title":"Neural Retrievers are Biased Towards LLM-Generated Content","created":"2023-10-31","cited_by_count":38,"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":"2502.12096","title":"Token Communications: A Large Model-Driven Framework for Cross-modal Context-aware Semantic Communications","created":"2025-02-17","cited_by_count":35,"area":null},{"id":"2602.06358","title":"SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass","created":"2026-02-06","cited_by_count":25,"area":null},{"id":"2509.20758","title":"SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs","created":"2025-09-25","cited_by_count":24,"area":null},{"id":"2310.08129","title":"Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewriting","created":"2023-10-12","cited_by_count":23,"area":null},{"id":"2512.04562","title":"LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models","created":"2025-12-04","cited_by_count":23,"area":null},{"id":"2402.19155","title":"Beyond Language Models: Byte Models are Digital World Simulators","created":"2024-02-29","cited_by_count":22,"area":null},{"id":"2507.06378","title":"Evaluating Morphological Alignment of Tokenizers in 70 Languages","created":"2025-07-08","cited_by_count":22,"area":null},{"id":"2402.14327","title":"Subobject-level Image Tokenization","created":"2024-02-22","cited_by_count":21,"area":null},{"id":"2503.00808","title":"Predictive Data Selection: The Data That Predicts Is the Data That Teaches","created":"2025-03-02","cited_by_count":21,"area":null},{"id":"2407.07723","title":"Lossless data compression by large models","created":"2024-06-24","cited_by_count":20,"area":null},{"id":"2410.21317","title":"MatExpert: Decomposing Materials Discovery by Mimicking Human Experts","created":"2024-10-26","cited_by_count":18,"area":null},{"id":"2310.11451","title":"Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective","created":"2023-10-17","cited_by_count":17,"area":null},{"id":"2404.03626","title":"Training LLMs over Neurally Compressed Text","created":"2024-04-04","cited_by_count":17,"area":null},{"id":"2405.16684","title":"gzip Predicts Data-dependent Scaling Laws","created":"2024-05-26","cited_by_count":16,"area":null},{"id":"2502.16163","title":"Large Language Model for Lossless Image Compression with Visual Prompts","created":"2025-02-22","cited_by_count":16,"area":null},{"id":"2509.16189","title":"Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences","created":"2025-09-19","cited_by_count":15,"area":null},{"id":"2603.10055","title":"Training Language Models via Neural Cellular Automata","created":"2026-03-09","cited_by_count":15,"area":null},{"id":"2310.05918","title":"Grokking as Compression: A Nonlinear Complexity Perspective","created":"2023-10-09","cited_by_count":14,"area":null},{"id":"2310.17639","title":"In-Context Learning Dynamics with Random Binary Sequences","created":"2023-10-26","cited_by_count":13,"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":"2403.03736","title":"Unifying Generation and Compression: Ultra-low bitrate Image Coding Via Multi-stage Transformer","created":"2024-03-06","cited_by_count":12,"area":null},{"id":"2404.16645","title":"Tele-FLM Technical Report","created":"2024-04-25","cited_by_count":12,"area":null},{"id":"2411.02142","title":"Training Compute-Optimal Protein Language Models","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2502.15957","title":"R$^3$Mem: Bridging Memory Retention and Retrieval via Reversible Compression","created":"2025-02-21","cited_by_count":12,"area":null},{"id":"2508.11214","title":"How Causal Abstraction Underpins Computational Explanation","created":"2025-08-15","cited_by_count":11,"area":null},{"id":"2404.08921","title":"PNeRV: Enhancing Spatial Consistency via Pyramidal Neural Representation for Videos","created":"2024-04-13","cited_by_count":10,"area":null},{"id":"2407.11784","title":"Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2411.12448","title":"Large Language Models for Lossless Image Compression: Next-Pixel Prediction in Language Space is All You Need","created":"2024-11-19","cited_by_count":10,"area":null},{"id":"2503.01505","title":"Lossy Neural Compression for Geospatial Analytics: A Review","created":"2025-03-03","cited_by_count":10,"area":null},{"id":"2503.19604","title":"GIViC: Generative Implicit Video Compression","created":"2025-03-25","cited_by_count":10,"area":null},{"id":"2406.07543","title":"Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning","created":"2024-06-11","cited_by_count":9,"area":null},{"id":"2408.02103","title":"Effective Demonstration Annotation for In-Context Learning via Language Model-Based Determinantal Point Process","created":"2024-08-04","cited_by_count":9,"area":null},{"id":"2510.12066","title":"AI Agents as Universal Task Solvers","created":"2025-10-14","cited_by_count":9,"area":null},{"id":"2410.14086","title":"In-context learning and Occam's razor","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2603.06242","title":"DC-Merge: Improving Model Merging with Directional Consistency","created":"2026-03-06","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":"2405.20657","title":"DORY: Deliberative Prompt Recovery for LLM","created":"2024-05-31","cited_by_count":7,"area":null},{"id":"2505.10946","title":"ToDMA: Large Model-Driven Massive Token Communications for Semantic Multiple Access","created":"2025-05-16","cited_by_count":7,"area":null},{"id":"2505.16477","title":"Advancing the Scientific Method with Large Language Models: From Hypothesis to Discovery","created":"2025-05-22","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":"2510.21909","title":"Explaining and Mitigating Crosslingual Tokenizer Inequities","created":"2025-10-24","cited_by_count":7,"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":"2408.15079","title":"BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline","created":"2024-08-27","cited_by_count":6,"area":null},{"id":"2505.15784","title":"Large Language Models as Computable Approximations to Solomonoff Induction","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2505.17010","title":"Understanding Prompt Tuning and In-Context Learning via Meta-Learning","created":"2025-05-22","cited_by_count":6,"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":"2509.22445","title":"Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2512.14697","title":"Spherical Leech Quantization for Visual Tokenization and Generation","created":"2025-12-16","cited_by_count":6,"area":null},{"id":"2605.30233","title":"Do Language Models Track Entities Across State Changes?","created":"2026-05-28","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":"2402.11656","title":"Integrating Pre-Trained Language Model with Physical Layer Communications","created":"2024-02-18","cited_by_count":5,"area":null},{"id":"2403.01384","title":"On the Compressibility of Quantized Large Language Models","created":"2024-03-03","cited_by_count":5,"area":null},{"id":"2404.07227","title":"Is Complexity an Illusion?","created":"2024-03-31","cited_by_count":5,"area":null},{"id":"2409.17836","title":"Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models","created":"2024-09-26","cited_by_count":5,"area":null},{"id":"2412.02857","title":"Measuring Fingerprints of Web-filtered Text Datasets and Fingerprint Propagation Through Training","created":"2024-12-03","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":"2604.07569","title":"Learning is Forgetting: LLM Training As Lossy Compression","created":"2026-04-08","cited_by_count":5,"area":null},{"id":"2404.01713","title":"Generative AI for Immersive Communication: The Next Frontier in Internet-of-Senses Through 6G","created":"2024-04-02","cited_by_count":4,"area":null},{"id":"2407.13493","title":"Training Foundation Models as Data Compression: On Information, Model Weights and Copyright Law","created":"2024-07-18","cited_by_count":4,"area":null},{"id":"2410.03040","title":"Geometry is All You Need: A Unified Taxonomy of Matrix and Tensor Factorization for Compression of Generative Language Models","created":"2024-10-03","cited_by_count":4,"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":"2602.15829","title":"Operationalising the Superficial Alignment Hypothesis via Task Complexity","created":"2026-02-17","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":"2607.14144","title":"The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale","created":"2026-07-14","cited_by_count":4,"area":null},{"id":"2410.05493","title":"An Information-Theoretic Approach to Understanding Transformers' In-Context Learning of Variable-Order Markov Chains","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2502.17024","title":"Towards Auto-Regressive Next-Token Prediction: In-Context Learning Emerges from Generalization","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2503.13431","title":"Measuring In-Context Computation Complexity via Hidden State Prediction","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2505.21441","title":"Autoencoding Random Forests","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2511.21882","title":"Closed-Loop Transformers: Autoregressive Modeling as Iterative Latent Equilibrium","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2602.04289","title":"Proxy Compression for Language Modeling","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2605.14831","title":"Interestingness as an Inductive Heuristic for Future Compression Progress","created":"2026-05-14","cited_by_count":3,"area":null},{"id":"2402.04582","title":"Dimensionality reduction can be used as a surrogate model for high-dimensional forward uncertainty quantification","created":"2024-02-07","cited_by_count":2,"area":null},{"id":"2406.14171","title":"Ranking LLMs by compression","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2408.16667","title":"Iterative Graph Alignment","created":"2024-08-29","cited_by_count":2,"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":"2412.09907","title":"IQViC: In-context, Question Adaptive Vision Compressor for Long-term Video Understanding LMMs","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2501.06802","title":"Unifying Two Types of Scaling Laws from the Perspective of Conditional Kolmogorov Complexity","created":"2025-01-12","cited_by_count":2,"area":null},{"id":"2505.11441","title":"Is Compression Really Linear with Code Intelligence?","created":"2025-05-16","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":"2505.17793","title":"Compression Hacking: A Supplementary Perspective on Informatics Properties of Language Models from Geometric Distortion","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2506.07557","title":"SELT: Self-Evaluation Tree Search for LLMs with Task Decomposition","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2508.02247","title":"ByteGen: A Tokenizer-Free Generative Model for Orderbook Events in Byte Space","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2509.11208","title":"Predictable Compression Failures: Order Sensitivity and Information Budgeting for Evidence-Grounded Binary Adjudication","created":"2025-09-14","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":"2601.20742","title":"Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification","created":"2026-01-28","cited_by_count":2,"area":null}],"next_cursor":"100"}