{"list":"other","total":92,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"1907.04809","title":"Variational Autoencoders and Nonlinear ICA: A Unifying Framework","created":"2019-07-10","cited_by_count":503},{"id":"2110.09348","title":"Understanding Dimensional Collapse in Contrastive Self-supervised Learning","created":"2021-10-18","cited_by_count":378},{"id":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"id":"1805.08651","title":"Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning","created":"2018-05-22","cited_by_count":282},{"id":"1605.06336","title":"Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA","created":"2016-05-20","cited_by_count":273},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"1906.02226","title":"Gradient-Based Neural DAG Learning","created":"2019-06-05","cited_by_count":227},{"id":"2102.08850","title":"Contrastive Learning Inverts the Data Generating Process","created":"2021-02-17","cited_by_count":221},{"id":"1706.01350","title":"Emergence of Invariance and Disentanglement in Deep Representations","created":"2017-06-05","cited_by_count":215},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"2102.11107","title":"Towards Causal Representation Learning","created":"2021-02-22","cited_by_count":209},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"2209.15430","title":"Relative representations enable zero-shot latent space communication","created":"2022-09-30","cited_by_count":191},{"id":"2310.02557","title":"Generalization in diffusion models arises from geometry-adaptive harmonic representations","created":"2023-10-04","cited_by_count":185},{"id":"2210.02885","title":"RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank","created":"2022-10-05","cited_by_count":153},{"id":"2205.11508","title":"Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods","created":"2022-05-23","cited_by_count":149},{"id":"2306.15063","title":"Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression","created":"2023-06-26","cited_by_count":146},{"id":"2203.16437","title":"Weakly supervised causal representation learning","created":"2022-03-30","cited_by_count":140},{"id":"2206.13188","title":"Self-supervised Learning in Remote Sensing: A Review","created":"2022-06-27","cited_by_count":137},{"id":"2007.10930","title":"Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding","created":"2020-07-21","cited_by_count":122},{"id":"1503.03167","title":"Deep Convolutional Inverse Graphics Network","created":"2015-03-11","cited_by_count":121},{"id":"2204.00673","title":"Learnable latent embeddings for joint behavioral and neural analysis","created":"2022-04-01","cited_by_count":117},{"id":"2305.16843","title":"Randomized Positional Encodings Boost Length Generalization of Transformers","created":"2023-05-26","cited_by_count":117},{"id":"2206.02574","title":"On the duality between contrastive and non-contrastive self-supervised learning","created":"2022-06-03","cited_by_count":108},{"id":"2306.00542","title":"Nonparametric Identifiability of Causal Representations from Unknown Interventions","created":"2023-06-01","cited_by_count":106},{"id":"2002.11537","title":"ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA","created":"2020-02-26","cited_by_count":102},{"id":"2106.05200","title":"Independent mechanism analysis, a new concept?","created":"2021-06-09","cited_by_count":97},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84},{"id":"2107.08221","title":"Visual Representation Learning Does Not Generalize Strongly Within the Same Domain","created":"2021-07-17","cited_by_count":61},{"id":"2303.09166","title":"Identifiability Results for Multimodal Contrastive Learning","created":"2023-03-16","cited_by_count":61},{"id":"2408.16737","title":"Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling","created":"2024-08-29","cited_by_count":61},{"id":"2307.02598","title":"Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation","created":"2023-07-05","cited_by_count":58},{"id":"2305.17225","title":"Causal Component Analysis","created":"2023-05-26","cited_by_count":56},{"id":"2208.06406","title":"Function Classes for Identifiable Nonlinear Independent Component Analysis","created":"2022-08-12","cited_by_count":53},{"id":"2011.04798","title":"Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE","created":"2020-11-09","cited_by_count":48},{"id":"2210.01738","title":"ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training","created":"2022-10-04","cited_by_count":47},{"id":"1905.12614","title":"Unsupervised Model Selection for Variational Disentangled Representation Learning","created":"2019-05-29","cited_by_count":46},{"id":"2406.06158","title":"Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning","created":"2024-06-10","cited_by_count":42},{"id":"2310.05327","title":"Provable Compositional Generalization for Object-Centric Learning","created":"2023-10-09","cited_by_count":41},{"id":"2302.02774","title":"The SSL Interplay: Augmentations, Inductive Bias, and Generalization","created":"2023-02-06","cited_by_count":40},{"id":"2407.00143","title":"InfoNCE: Identifying the Gap Between Theory and Practice","created":"2024-06-28","cited_by_count":40},{"id":"2306.09643","title":"BISCUIT: Causal Representation Learning from Binary Interactions","created":"2023-06-16","cited_by_count":38},{"id":"2106.07115","title":"Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective","created":"2021-06-14","cited_by_count":37},{"id":"2303.15438","title":"On the Stepwise Nature of Self-Supervised Learning","created":"2023-03-27","cited_by_count":36},{"id":"2310.09562","title":"Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?","created":"2023-10-14","cited_by_count":35},{"id":"2202.05826","title":"End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking","created":"2022-02-11","cited_by_count":33},{"id":"2210.11464","title":"Self-Supervised Learning via Maximum Entropy Coding","created":"2022-10-20","cited_by_count":33},{"id":"2310.15709","title":"Causal Representation Learning Made Identifiable by Grouping of Observational Variables","created":"2023-10-24","cited_by_count":32},{"id":"2409.02772","title":"Unifying Causal Representation Learning with the Invariance Principle","created":"2024-09-04","cited_by_count":31},{"id":"2410.21869","title":"Cross-Entropy Is All You Need To Invert the Data Generating Process","created":"2024-10-29","cited_by_count":31},{"id":"2206.02416","title":"Embrace the Gap: VAEs Perform Independent Mechanism Analysis","created":"2022-06-06","cited_by_count":28},{"id":"2206.13378","title":"Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning","created":"2022-06-27","cited_by_count":26},{"id":"2405.13888","title":"Marrying Causal Representation Learning with Dynamical Systems for Science","created":"2024-05-22","cited_by_count":23},{"id":"2402.04875","title":"On Provable Length and Compositional Generalization","created":"2024-02-07","cited_by_count":22},{"id":"2310.01211","title":"From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication","created":"2023-10-02","cited_by_count":21},{"id":"2405.01964","title":"Position: Understanding LLMs Requires More Than Statistical Generalization","created":"2024-05-03","cited_by_count":21},{"id":"2410.08258","title":"In Search of Forgotten Domain Generalization","created":"2024-10-10","cited_by_count":21},{"id":"2403.11391","title":"Investigating the Benefits of Projection Head for Representation Learning","created":"2024-03-18","cited_by_count":20},{"id":"2411.07784","title":"Interaction Asymmetry: A General Principle for Learning Composable Abstractions","created":"2024-11-12","cited_by_count":20},{"id":"2006.10944","title":"Independent Innovation Analysis for Nonlinear Vector Autoregressive Process","created":"2020-06-19","cited_by_count":19},{"id":"2206.01342","title":"Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning","created":"2022-06-02","cited_by_count":19},{"id":"2311.08815","title":"Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations","created":"2023-11-15","cited_by_count":17},{"id":"2210.09879","title":"Unsupervised visualization of image datasets using contrastive learning","created":"2022-10-18","cited_by_count":16},{"id":"2406.14302","title":"Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning","created":"2024-06-20","cited_by_count":16},{"id":"2207.10081","title":"What Do We Maximize in Self-Supervised Learning?","created":"2022-07-20","cited_by_count":15},{"id":"2410.23501","title":"All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling","created":"2024-10-30","cited_by_count":14},{"id":"2410.06303","title":"Compositional Risk Minimization","created":"2024-10-08","cited_by_count":13},{"id":"2406.13371","title":"Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment","created":"2024-06-19","cited_by_count":12},{"id":"2209.14905","title":"Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations","created":"2022-09-29","cited_by_count":10},{"id":"2406.15057","title":"Latent Space Translation via Inverse Relative Projection","created":"2024-06-21","cited_by_count":10},{"id":"2311.18048","title":"An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis","created":"2023-11-29","cited_by_count":9},{"id":"2403.05726","title":"Augmentations vs Algorithms: What Works in Self-Supervised Learning","created":"2024-03-08","cited_by_count":9},{"id":"2502.09252","title":"On the Importance of Embedding Norms in Self-Supervised Learning","created":"2025-02-13","cited_by_count":9},{"id":"2406.10743","title":"Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?","created":"2024-06-15","cited_by_count":8},{"id":"2307.08913","title":"Towards the Sparseness of Projection Head in Self-Supervised Learning","created":"2023-07-18","cited_by_count":4}],"next_cursor":null}