{"total":51,"rows":[{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528,"area":null},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2201.02609","title":"Generalized Category Discovery","created":"2022-01-07","cited_by_count":211,"area":null},{"id":"2308.09718","title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training","created":"2023-08-18","cited_by_count":86,"area":null},{"id":"2403.19546","title":"Croissant: A Metadata Format for ML-Ready Datasets","created":"2024-03-28","cited_by_count":81,"area":null},{"id":"2207.02206","title":"Segmenting Moving Objects via an Object-Centric Layered Representation","created":"2022-07-05","cited_by_count":63,"area":null},{"id":"2406.10328","title":"From Pixels to Prose: A Large Dataset of Dense Image Captions","created":"2024-06-14","cited_by_count":54,"area":"mllm"},{"id":"2301.02560","title":"GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition","created":"2023-01-05","cited_by_count":50,"area":null},{"id":"2405.15613","title":"Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach","created":"2024-05-24","cited_by_count":50,"area":null},{"id":"2205.09723","title":"Robust and Efficient Medical Imaging with Self-Supervision","created":"2022-05-19","cited_by_count":40,"area":null},{"id":"2206.09191","title":"Gender Artifacts in Visual Datasets","created":"2022-06-18","cited_by_count":38,"area":null},{"id":"2402.03310","title":"V-IRL: Grounding Virtual Intelligence in Real Life","created":"2024-02-05","cited_by_count":35,"area":null},{"id":"2212.10678","title":"Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2305.15407","title":"Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets","created":"2023-05-24","cited_by_count":27,"area":"mllm"},{"id":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","cited_by_count":26,"area":null},{"id":"2403.17381","title":"Application-Driven Innovation in Machine Learning","created":"2024-03-26","cited_by_count":24,"area":null},{"id":"2207.03860","title":"Consecutive Pretraining: A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain","created":"2022-07-08","cited_by_count":22,"area":null},{"id":"2310.01755","title":"ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms","created":"2023-10-03","cited_by_count":22,"area":null},{"id":"2206.09132","title":"Pre-training Vision Transformers with Formula-driven Supervised Learning","created":"2022-06-18","cited_by_count":21,"area":null},{"id":"2303.01112","title":"Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves","created":"2023-03-02","cited_by_count":20,"area":null},{"id":"2503.12127","title":"Hyperbolic Safety-Aware Vision-Language Models","created":"2025-03-15","cited_by_count":17,"area":"mllm"},{"id":"2203.04706","title":"Data Representativity for Machine Learning and AI Systems","created":"2022-03-09","cited_by_count":15,"area":null},{"id":"2408.00677","title":"Scaling Backwards: Minimal Synthetic Pre-training?","created":"2024-08-01","cited_by_count":14,"area":null},{"id":"2303.05689","title":"Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severity","created":"2023-03-10","cited_by_count":13,"area":null},{"id":"2212.12522","title":"An Exact Mapping From ReLU Networks to Spiking Neural Networks","created":"2022-12-23","cited_by_count":12,"area":null},{"id":"2307.14710","title":"Pre-training Vision Transformers with Very Limited Synthesized Images","created":"2023-07-27","cited_by_count":12,"area":null},{"id":"2312.11463","title":"Appearance-Based Refinement for Object-Centric Motion Segmentation","created":"2023-12-18","cited_by_count":11,"area":null},{"id":"2404.17249","title":"Making Better Use of Unlabelled Data in Bayesian Active Learning","created":"2024-04-26","cited_by_count":10,"area":null},{"id":"2309.02401","title":"Prototype-based Dataset Comparison","created":"2023-09-05","cited_by_count":9,"area":null},{"id":"2306.12816","title":"XAI-TRIS: Non-linear image benchmarks to quantify false positive post-hoc attribution of feature importance","created":"2023-06-22","cited_by_count":7,"area":null},{"id":"2303.17176","title":"A View From Somewhere: Human-Centric Face Representations","created":"2023-03-30","cited_by_count":6,"area":null},{"id":"2409.00768","title":"Rethinking Image Super-Resolution from Training Data Perspectives","created":"2024-09-01","cited_by_count":6,"area":null},{"id":"2505.07019","title":"A Vision-Language Foundation Model for Leaf Disease Identification","created":"2025-05-11","cited_by_count":6,"area":"mllm"},{"id":"2210.10820","title":"VTC: Improving Video-Text Retrieval with User Comments","created":"2022-10-19","cited_by_count":5,"area":null},{"id":"2311.06231","title":"Learning Human Action Recognition Representations Without Real Humans","created":"2023-11-10","cited_by_count":5,"area":null},{"id":"2206.07125","title":"Self-Supervised Pretraining for Differentially Private Learning","created":"2022-06-14","cited_by_count":4,"area":null},{"id":"2210.00715","title":"WorldGen: A Large Scale Generative Simulator","created":"2022-10-03","cited_by_count":4,"area":null},{"id":"2304.14376","title":"Zero-shot Unsupervised Transfer Instance Segmentation","created":"2023-04-27","cited_by_count":4,"area":null},{"id":"2210.02570","title":"Revisiting Structured Dropout","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2210.04076","title":"Robustness of Unsupervised Representation Learning without Labels","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2403.19669","title":"Analyzing the Roles of Language and Vision in Learning from Limited Data","created":"2024-02-15","cited_by_count":2,"area":null},{"id":"2406.06407","title":"A Taxonomy of Challenges to Curating Fair Datasets","created":"2024-06-10","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":"2411.00266","title":"A Systematic Review of NeurIPS Dataset Management Practices","created":"2024-10-31","cited_by_count":2,"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":"2211.15060","title":"Interactive Visual Feature Search","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2306.11710","title":"Data-Driven but Privacy-Conscious: Pedestrian Dataset De-identification via Full-Body Person Synthesis","created":"2023-06-20","cited_by_count":0,"area":null},{"id":"2409.14378","title":"Sparse Low-Ranked Self-Attention Transformer for Remaining Useful Lifetime Prediction of Optical Fiber Amplifiers","created":"2024-09-22","cited_by_count":0,"area":null},{"id":"2502.18056","title":"Escaping The Big Data Paradigm in Self-Supervised Representation Learning","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2511.17135","title":"A Multi-Stage Optimization Framework for Deploying Learned Image Compression on FPGAs","created":"2025-11-21","cited_by_count":0,"area":null}],"next_cursor":null}