{"total":92,"rows":[{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177,"area":null},{"id":"2112.05135","title":"PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures","created":"2021-12-09","cited_by_count":131,"area":null},{"id":"2305.01649","title":"Generalizing Dataset Distillation via Deep Generative Prior","created":"2023-05-02","cited_by_count":126,"area":null},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108,"area":null},{"id":"2206.11488","title":"On the Importance and Applicability of Pre-Training for Federated Learning","created":"2022-06-23","cited_by_count":71,"area":null},{"id":"2112.05143","title":"GAN-Supervised Dense Visual Alignment","created":"2021-12-09","cited_by_count":62,"area":null},{"id":"2310.15160","title":"FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models","created":"2023-10-23","cited_by_count":61,"area":null},{"id":"2206.02465","title":"Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning","created":"2022-06-06","cited_by_count":52,"area":null},{"id":"2401.01862","title":"A Vision Check-up for Language Models","created":"2024-01-03","cited_by_count":36,"area":null},{"id":"2211.12491","title":"ModelDiff: A Framework for Comparing Learning Algorithms","created":"2022-11-22","cited_by_count":30,"area":null},{"id":"2411.02372","title":"Learning General-Purpose Biomedical Volume Representations using Randomized Synthesis","created":"2024-11-04","cited_by_count":29,"area":null},{"id":"2211.16412","title":"Procedural Image Programs for Representation Learning","created":"2022-11-29","cited_by_count":28,"area":null},{"id":"2112.00054","title":"Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data","created":"2021-11-30","cited_by_count":26,"area":"synth"},{"id":"2403.12448","title":"Do Generated Data Always Help Contrastive Learning?","created":"2024-03-19","cited_by_count":25,"area":"diffusion"},{"id":"2206.09132","title":"Pre-training Vision Transformers with Formula-driven Supervised Learning","created":"2022-06-18","cited_by_count":21,"area":null},{"id":"2306.06076","title":"Differentially Private Image Classification by Learning Priors from Random Processes","created":"2023-06-08","cited_by_count":19,"area":null},{"id":"2406.05184","title":"The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better","created":"2024-06-07","cited_by_count":19,"area":null},{"id":"2410.10811","title":"Deep Linear Probe Generators for Weight Space Learning","created":"2024-10-14","cited_by_count":17,"area":"mechinterp"},{"id":"2406.01264","title":"FreeTumor: Advance Tumor Segmentation via Large-Scale Tumor Synthesis","created":"2024-06-03","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":"2310.04780","title":"IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers","created":"2023-10-07","cited_by_count":14,"area":null},{"id":"2408.00677","title":"Scaling Backwards: Minimal Synthetic Pre-training?","created":"2024-08-01","cited_by_count":14,"area":null},{"id":"2502.19402","title":"General Intelligence Requires Reward-based Pretraining","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2503.01167","title":"Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data","created":"2025-03-03","cited_by_count":12,"area":"synth"},{"id":"2311.13028","title":"DMLR: Data-centric Machine Learning Research -- Past, Present and Future","created":"2023-11-21","cited_by_count":11,"area":null},{"id":"2601.21725","title":"Procedural Pretraining: Warming Up Language Models with Abstract Data","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2411.12817","title":"What Makes a Good Dataset for Knowledge Distillation?","created":"2024-11-19","cited_by_count":9,"area":"distill"},{"id":"2505.22308","title":"Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic Reasoning","created":"2025-05-28","cited_by_count":9,"area":"lr"},{"id":"2207.00052","title":"Visual Pre-training for Navigation: What Can We Learn from Noise?","created":"2022-06-30","cited_by_count":8,"area":null},{"id":"2511.13945","title":"Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers","created":"2025-11-17","cited_by_count":8,"area":null},{"id":"2112.00725","title":"The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image","created":"2021-12-01","cited_by_count":7,"area":null},{"id":"2210.10913","title":"Palm up: Playing in the Latent Manifold for Unsupervised Pretraining","created":"2022-10-19","cited_by_count":7,"area":null},{"id":"2204.01108","title":"Adjusting for Bias with Procedural Data","created":"2022-04-03","cited_by_count":6,"area":null},{"id":"2204.04950","title":"Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2602.19946","title":"When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators","created":"2026-02-23","cited_by_count":6,"area":"diffusion"},{"id":"2109.15101","title":"Compositional generalization in semantic parsing with pretrained transformers","created":"2021-09-30","cited_by_count":5,"area":null},{"id":"2307.08727","title":"Learning to Count without Annotations","created":"2023-07-17","cited_by_count":5,"area":null},{"id":"2307.15977","title":"Model Synthesis for Zero-Shot Model Attribution","created":"2023-07-29","cited_by_count":5,"area":null},{"id":"2212.13967","title":"Extreme Image Transformations Affect Humans and Machines Differently","created":"2022-11-30","cited_by_count":4,"area":null},{"id":"2303.15888","title":"Projected Latent Distillation for Data-Agnostic Consolidation in Distributed Continual Learning","created":"2023-03-28","cited_by_count":4,"area":null},{"id":"2305.17520","title":"USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolution","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2311.06224","title":"Harnessing Synthetic Datasets: The Role of Shape Bias in Deep Neural Network Generalization","created":"2023-11-10","cited_by_count":4,"area":null},{"id":"2401.14211","title":"Communication-Efficient Federated Learning through Adaptive Weight Clustering and Server-Side Distillation","created":"2024-01-25","cited_by_count":4,"area":null},{"id":"2402.18905","title":"Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2403.10911","title":"Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation","created":"2024-03-16","cited_by_count":4,"area":"diffusion"},{"id":"2205.05167","title":"Robustness of Humans and Machines on Object Recognition with Extreme Image Transformations","created":"2022-05-09","cited_by_count":3,"area":null},{"id":"2310.02876","title":"Hate Speech Detection in Limited Data Contexts using Synthetic Data Generation","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2403.05966","title":"Can Generative Models Improve Self-Supervised Representation Learning?","created":"2024-03-09","cited_by_count":3,"area":null},{"id":"2410.00511","title":"Pre-training with Synthetic Patterns for Audio","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2410.24213","title":"Learning Video Representations without Natural Videos","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2602.05184","title":"Towards Worst-Case Guarantees with Scale-Aware Interpretability","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2607.11064","title":"WiFi-JEPA: Self-supervised Learning for WiFi-CSI 3D Human Pose Estimation","created":"2026-07-13","cited_by_count":3,"area":null},{"id":"2303.12722","title":"Learning Fractals by Gradient Descent","created":"2023-03-14","cited_by_count":2,"area":null},{"id":"2409.02189","title":"Collaboratively Learning Federated Models from Noisy Decentralized Data","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2409.06665","title":"Data Collection-free Masked Video Modeling","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2504.12833","title":"SPIE: Semantic and Structural Post-Training of Image Editing Diffusion Models with AI feedback","created":"2025-04-17","cited_by_count":2,"area":"diffusion"},{"id":"2207.01110","title":"Data-Driven Modeling of Noise Time Series with Convolutional Generative Adversarial Networks","created":"2022-07-03","cited_by_count":1,"area":null},{"id":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2409.13235","title":"Balancing Label Imbalance in Federated Environments Using Only Mixup and Artificially-Labeled Noise","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2411.17467","title":"Semantic-Free Procedural 3D Shapes Are Surprisingly Good Teachers","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2411.17584","title":"Pre-training for Action Recognition with Automatically Generated Fractal Datasets","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2504.10201","title":"VibrantLeaves: A principled parametric image generator for training deep restoration models","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2506.19465","title":"Stylized Structural Patterns for Improved Neural Network Pre-training","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2508.08821","title":"3DFroMLLM: 3D Prototype Generation only from Pretrained Multimodal LLMs","created":"2025-08-12","cited_by_count":1,"area":"mllm"},{"id":"2509.25104","title":"Towards generalizable deep ptychography neural networks","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2510.24159","title":"Self-supervised Synthetic Pretraining for Inference of Stellar Mass Embedded in Dense Gas","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2603.13467","title":"Learning Not To Interfere: Adapting Experts For Model Merging","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2609.30063","title":"Self-Play Pretraining with Zero Data","created":"2026-09-24","cited_by_count":1,"area":"synth"},{"id":"2210.01257","title":"Testing predictions of representation cost theory with CNNs","created":"2022-10-03","cited_by_count":0,"area":null},{"id":"2211.06441","title":"Metaphors We Learn By","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2310.07725","title":"Extreme Image Transformations Facilitate Robust Latent Object Representations","created":"2023-09-19","cited_by_count":0,"area":null},{"id":"2403.08592","title":"Data-Efficient Sleep Staging with Synthetic Time Series Pretraining","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2404.07212","title":"Hybrid Training of Denoising Networks to Improve the Texture Acutance of Digital Cameras","created":"2024-02-20","cited_by_count":0,"area":null},{"id":"2409.08884","title":"Detect Fake with Fake: Leveraging Synthetic Data-driven Representation for Synthetic Image Detection","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2502.01490","title":"MoireDB: Formula-generated Interference-fringe Image Dataset","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2503.07587","title":"Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru","created":"2025-03-10","cited_by_count":0,"area":"driving"},{"id":"2506.20897","title":"Development of MR spectral analysis method robust against static magnetic field inhomogeneity","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2508.11697","title":"Separating Knowledge and Perception with Procedural Data","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2508.15141","title":"Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2512.05539","title":"Ideal Observer for Segmentation of Dead Leaves Images","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2601.17189","title":"Rethinking Benchmarks for Differentially Private Image Classification","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2603.25109","title":"MoireMix: A Formula-Based Data Augmentation for Improving Image Classification Robustness","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.12335","title":"SynMulti: Synthetic-to-Real Learning for Multimodal Video Understanding","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2606.00558","title":"Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.02177","title":"Low-Pass Flow Matching","created":"2026-06-01","cited_by_count":0,"area":"diffusion"},{"id":"2606.20347","title":"Critical Percolation as a Synthetic Data Model for Interpretability","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.07470","title":"A Theory of Contrastive Learning with Natural Images","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.02869","title":"Contrast-invariant deep ptychography neural networks","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.24759","title":"IDeaL: Data-Free Multi-Teacher Distillation via Improved Dead Leaves","created":"2026-08-25","cited_by_count":0,"area":"distill"},{"id":"2609.17831","title":"Procedural Pretraining for Molecular Property Prediction","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.37631","title":"Procedural Core: A Compact Recurrent Initialization for Vision Transformers","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}