{"total":69,"rows":[{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344,"area":null},{"id":"2309.10668","title":"Language Modeling Is Compression","created":"2023-09-19","cited_by_count":225,"area":null},{"id":"2212.10375","title":"Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering","created":"2022-12-20","cited_by_count":161,"area":null},{"id":"2111.13171","title":"Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks","created":"2021-11-25","cited_by_count":70,"area":null},{"id":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63,"area":null},{"id":"2405.18653","title":"Recent Advances of Foundation Language Models-based Continual Learning: A Survey","created":"2024-05-28","cited_by_count":46,"area":null},{"id":"2102.05289","title":"Bayesian Inference with Certifiable Adversarial Robustness","created":"2021-02-10","cited_by_count":26,"area":null},{"id":"2206.08684","title":"Sparse Double Descent: Where Network Pruning Aggravates Overfitting","created":"2022-06-17","cited_by_count":26,"area":null},{"id":"2310.13620","title":"Bridging Information-Theoretic and Geometric Compression in Language Models","created":"2023-10-20","cited_by_count":26,"area":null},{"id":"2103.03872","title":"Rissanen Data Analysis: Examining Dataset Characteristics via Description Length","created":"2021-03-05","cited_by_count":22,"area":null},{"id":"2109.03853","title":"A Bayesian Framework for Information-Theoretic Probing","created":"2021-09-08","cited_by_count":22,"area":null},{"id":"2110.03618","title":"Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP","created":"2021-10-07","cited_by_count":21,"area":null},{"id":"2201.13011","title":"On the Power-Law Hessian Spectrums in Deep Learning","created":"2022-01-31","cited_by_count":16,"area":null},{"id":"2306.08448","title":"Kalman Filter for Online Classification of Non-Stationary Data","created":"2023-06-14","cited_by_count":15,"area":null},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2210.07931","title":"Sequential Learning Of Neural Networks for Prequential MDL","created":"2022-10-14","cited_by_count":13,"area":null},{"id":"2410.14817","title":"A Complexity-Based Theory of Compositionality","created":"2024-10-18","cited_by_count":13,"area":null},{"id":"2209.03580","title":"Conformal Methods for Quantifying Uncertainty in Spatiotemporal Data: A Survey","created":"2022-09-08","cited_by_count":11,"area":null},{"id":"2402.03254","title":"Minimum Description Length and Generalization Guarantees for Representation Learning","created":"2024-02-05","cited_by_count":11,"area":null},{"id":"2211.13239","title":"Relating Regularization and Generalization through the Intrinsic Dimension of Activations","created":"2022-11-23","cited_by_count":9,"area":null},{"id":"2312.01619","title":"How Many Validation Labels Do You Need? Exploring the Design Space of Label-Efficient Model Ranking","created":"2023-12-04","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":"2307.04317","title":"Text Descriptions are Compressive and Invariant Representations for Visual Learning","created":"2023-07-10","cited_by_count":7,"area":null},{"id":"2305.05461","title":"What is the best recipe for character-level encoder-only modelling?","created":"2023-05-09","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":"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":"2412.03587","title":"Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models","created":"2024-11-26","cited_by_count":5,"area":null},{"id":"2504.15208","title":"Compute-Optimal LLMs Provably Generalize Better With Scale","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2111.02770","title":"Representation Edit Distance as a Measure of Novelty","created":"2021-11-04","cited_by_count":4,"area":null},{"id":"2103.13272","title":"Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages","created":"2021-03-24","cited_by_count":3,"area":null},{"id":"2105.13978","title":"What Is Considered Complete for Visual Recognition?","created":"2021-05-28","cited_by_count":3,"area":null},{"id":"2210.06741","title":"Why self-attention is Natural for Sequence-to-Sequence Problems? A Perspective from Symmetries","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2301.13330","title":"Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference","created":"2023-01-30","cited_by_count":3,"area":null},{"id":"2309.03710","title":"A State Representation for Diminishing Rewards","created":"2023-09-07","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":"2505.07503","title":"Identifying Causal Direction via Variational Bayesian Compression","created":"2025-05-12","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":"2103.12496","title":"Revisiting Self-Supervised Monocular Depth Estimation","created":"2021-03-23","cited_by_count":2,"area":null},{"id":"2107.05481","title":"Prequential MDL for Causal Structure Learning with Neural Networks","created":"2021-07-02","cited_by_count":2,"area":null},{"id":"2210.02989","title":"SynBench: Task-Agnostic Benchmarking of Pretrained Representations using Synthetic Data","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2310.01144","title":"The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks","created":"2023-10-02","cited_by_count":2,"area":null},{"id":"2412.08210","title":"Unicorn: Unified Neural Image Compression with One Number Reconstruction","created":"2024-12-11","cited_by_count":2,"area":null},{"id":"2506.12903","title":"Variational Learning Finds Flatter Solutions at the Edge of Stability","created":"2025-06-15","cited_by_count":2,"area":null},{"id":"2607.18433","title":"Intelligence from Learnable Novelty","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2607.27617","title":"Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2210.13554","title":"Weight Fixing Networks","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2310.13856","title":"Implications of Annotation Artifacts in Edge Probing Test Datasets","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2502.12302","title":"Chaotic Map based Compression Approach to Classification","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2505.09855","title":"An evolutionary perspective on modes of learning in Transformers","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2505.13657","title":"Clarifying orthography: Orthographic transparency as compressibility","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2510.01105","title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2602.14481","title":"On the Rate-Distortion-Complexity Tradeoff for Semantic Communication","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2606.04834","title":"Prediction Under Imperfect Compression: A Theory of Approximate MDL","created":"2026-06-03","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":"2105.12115","title":"Calibration and Uncertainty Quantification of Bayesian Convolutional Neural Networks for Geophysical Applications","created":"2021-05-25","cited_by_count":0,"area":null},{"id":"2111.01662","title":"OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression","created":"2021-11-02","cited_by_count":0,"area":null},{"id":"2206.01251","title":"Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods","created":"2022-06-02","cited_by_count":0,"area":null},{"id":"2207.08258","title":"Minimum Description Length Control","created":"2022-07-17","cited_by_count":0,"area":null},{"id":"2303.15464","title":"Mathematical Challenges in Deep Learning","created":"2023-03-24","cited_by_count":0,"area":null},{"id":"2504.00395","title":"A Theory of Machine Understanding via the Minimum Description Length Principle","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2504.11986","title":"Large Language Models as Quasi-crystals: Coherence Without Repetition in Generative Text","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2510.02629","title":"Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.18934","title":"Position: Many generalization measures for deep learning are fragile","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2601.04728","title":"Excess Description Length of Learning Generalizable Predictors","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2603.25839","title":"A Compression Perspective on Simplicity Bias","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.31503","title":"How can embedding models bind concepts?","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.21593","title":"Geometric and Information Compression of Representations in Deep Learning","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2609.28603","title":"Learning to Discover Interesting Mathematics","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.20396","title":"From Human Corrections to Learned Segmentations: A Critical Mathematical Review of Information, Learning, and Human Effort","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}