{"total":2539,"rows":[{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160,"area":null},{"id":"2203.05794","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","created":"2022-03-11","cited_by_count":801,"area":null},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293,"area":null},{"id":"2101.10979","title":"Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation","created":"2021-01-26","cited_by_count":268,"area":null},{"id":"2312.15185","title":"emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation","created":"2023-12-23","cited_by_count":205,"area":null},{"id":"2412.07236","title":"CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding","created":"2024-12-10","cited_by_count":199,"area":null},{"id":"2203.01517","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","created":"2022-03-03","cited_by_count":172,"area":null},{"id":"2203.06125","title":"Protein Representation Learning by Geometric Structure Pretraining","created":"2022-03-11","cited_by_count":162,"area":null},{"id":"2309.17448","title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","created":"2023-09-29","cited_by_count":155,"area":null},{"id":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139,"area":null},{"id":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133,"area":null},{"id":"2111.00595","title":"TorchXRayVision: A library of chest X-ray datasets and models","created":"2021-10-31","cited_by_count":131,"area":null},{"id":"2209.01712","title":"ChemBERTa-2: Towards Chemical Foundation Models","created":"2022-09-05","cited_by_count":127,"area":null},{"id":"2210.04620","title":"FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings","created":"2022-10-10","cited_by_count":125,"area":null},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123,"area":null},{"id":"2402.05862","title":"Let Your Graph Do the Talking: Encoding Structured Data for LLMs","created":"2024-02-08","cited_by_count":118,"area":null},{"id":"2204.00673","title":"Learnable latent embeddings for joint behavioral and neural analysis","created":"2022-04-01","cited_by_count":117,"area":null},{"id":"2108.01775","title":"Solo-learn: A Library of Self-supervised Methods for Visual Representation Learning","created":"2021-08-03","cited_by_count":116,"area":null},{"id":"2106.06047","title":"Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning","created":"2021-06-10","cited_by_count":111,"area":null},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109,"area":null},{"id":"2307.01984","title":"The KiTS21 Challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CT","created":"2023-07-05","cited_by_count":103,"area":null},{"id":"2111.13489","title":"SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings","created":"2021-11-26","cited_by_count":95,"area":null},{"id":"2206.07632","title":"Exploring Chemical Space with Score-based Out-of-distribution Generation","created":"2022-06-06","cited_by_count":95,"area":null},{"id":"2310.14918","title":"ARNIQA: Learning Distortion Manifold for Image Quality Assessment","created":"2023-10-20","cited_by_count":89,"area":null},{"id":"2110.05266","title":"Chaos as an interpretable benchmark for forecasting and data-driven modelling","created":"2021-10-11","cited_by_count":88,"area":null},{"id":"2309.08638","title":"Anchor Points: Benchmarking Models with Much Fewer Examples","created":"2023-09-14","cited_by_count":86,"area":null},{"id":"2307.06250","title":"Identifiability Guarantees for Causal Disentanglement from Soft Interventions","created":"2023-07-12","cited_by_count":84,"area":null},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81,"area":null},{"id":"2207.14502","title":"Language Models Can Teach Themselves to Program Better","created":"2022-07-29","cited_by_count":78,"area":null},{"id":"2210.01189","title":"Rank-N-Contrast: Learning Continuous Representations for Regression","created":"2022-10-03","cited_by_count":76,"area":null},{"id":"2206.02909","title":"Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data","created":"2022-06-06","cited_by_count":75,"area":null},{"id":"2311.11666","title":"OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning","created":"2023-11-20","cited_by_count":75,"area":null},{"id":"2412.13678","title":"Clio: Privacy-Preserving Insights into Real-World AI Use","created":"2024-12-18","cited_by_count":72,"area":null},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70,"area":null},{"id":"2402.17229","title":"Preserving Fairness Generalization in Deepfake Detection","created":"2024-02-27","cited_by_count":70,"area":null},{"id":"2103.13646","title":"Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels","created":"2021-03-25","cited_by_count":69,"area":null},{"id":"2103.16392","title":"CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning","created":"2021-03-30","cited_by_count":69,"area":null},{"id":"2303.02760","title":"Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes","created":"2023-03-05","cited_by_count":68,"area":null},{"id":"2311.03757","title":"Manifold learning: what, how, and why","created":"2023-11-07","cited_by_count":68,"area":null},{"id":"2201.00058","title":"Representation Topology Divergence: A Method for Comparing Neural Network Representations","created":"2021-12-31","cited_by_count":66,"area":null},{"id":"2110.07588","title":"Playing for 3D Human Recovery","created":"2021-10-14","cited_by_count":64,"area":null},{"id":"2402.18225","title":"CogBench: a large language model walks into a psychology lab","created":"2024-02-28","cited_by_count":63,"area":null},{"id":"2207.07180","title":"Contrastive Adapters for Foundation Model Group Robustness","created":"2022-07-14","cited_by_count":62,"area":null},{"id":"2309.09968","title":"Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees","created":"2023-09-18","cited_by_count":62,"area":null},{"id":"2202.11684","title":"MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Dataset","created":"2022-02-23","cited_by_count":61,"area":null},{"id":"2206.14262","title":"Supervised Training of Conditional Monge Maps","created":"2022-06-28","cited_by_count":61,"area":null},{"id":"2209.11883","title":"Hebbian Deep Learning Without Feedback","created":"2022-09-23","cited_by_count":61,"area":null},{"id":"2311.07125","title":"Attention-Challenging Multiple Instance Learning for Whole Slide Image Classification","created":"2023-11-13","cited_by_count":61,"area":null},{"id":"2212.10378","title":"Data Curation Alone Can Stabilize In-context Learning","created":"2022-12-20","cited_by_count":59,"area":null},{"id":"2604.07729","title":"Emotion Concepts and their Function in a Large Language Model","created":"2026-04-09","cited_by_count":57,"area":null},{"id":"2103.16329","title":"E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoT","created":"2021-03-30","cited_by_count":56,"area":null},{"id":"2106.13200","title":"Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy","created":"2021-06-24","cited_by_count":55,"area":null},{"id":"2201.04182","title":"HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning","created":"2022-01-11","cited_by_count":55,"area":null},{"id":"2112.07782","title":"Deciphering antibody affinity maturation with language models and weakly supervised learning","created":"2021-12-14","cited_by_count":53,"area":null},{"id":"2410.20964","title":"DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning","created":"2024-10-28","cited_by_count":53,"area":null},{"id":"2104.07059","title":"Neural population geometry: An approach for understanding biological and artificial neural networks","created":"2021-04-14","cited_by_count":52,"area":null},{"id":"2203.14309","title":"DeepDPM: Deep Clustering With an Unknown Number of Clusters","created":"2022-03-27","cited_by_count":52,"area":null},{"id":"2305.03210","title":"AttentionViz: A Global View of Transformer Attention","created":"2023-05-04","cited_by_count":50,"area":null},{"id":"2101.01600","title":"Learning the Predictability of the Future","created":"2021-01-01","cited_by_count":49,"area":null},{"id":"2209.14803","title":"polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics","created":"2022-09-29","cited_by_count":48,"area":null},{"id":"2303.13662","title":"Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment","created":"2023-03-23","cited_by_count":48,"area":null},{"id":"2301.05768","title":"RxRx1: A Dataset for Evaluating Experimental Batch Correction Methods","created":"2023-01-13","cited_by_count":46,"area":null},{"id":"2404.04689","title":"Multicalibration for Confidence Scoring in LLMs","created":"2024-04-06","cited_by_count":46,"area":null},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46,"area":null},{"id":"2102.09427","title":"Deep Learning for Suicide and Depression Identification with Unsupervised Label Correction","created":"2021-02-18","cited_by_count":45,"area":null},{"id":"2207.10362","title":"LocVTP: Video-Text Pre-training for Temporal Localization","created":"2022-07-21","cited_by_count":44,"area":null},{"id":"2210.03115","title":"SimPer: Simple Self-Supervised Learning of Periodic Targets","created":"2022-10-06","cited_by_count":44,"area":null},{"id":"2203.10897","title":"Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression","created":"2022-03-21","cited_by_count":43,"area":null},{"id":"2308.02053","title":"The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations","created":"2023-08-03","cited_by_count":41,"area":null},{"id":"2502.18968","title":"Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles","created":"2025-02-26","cited_by_count":41,"area":null},{"id":"2201.13291","title":"Metrics for saliency map evaluation of deep learning explanation methods","created":"2022-01-31","cited_by_count":40,"area":null},{"id":"2206.07948","title":"Forming Effective Human-AI Teams: Building Machine Learning Models that Complement the Capabilities of Multiple Experts","created":"2022-06-16","cited_by_count":40,"area":null},{"id":"2304.04662","title":"SELFormer: Molecular Representation Learning via SELFIES Language Models","created":"2023-04-10","cited_by_count":40,"area":null},{"id":"2401.06712","title":"Few-Shot Detection of Machine-Generated Text using Style Representations","created":"2024-01-12","cited_by_count":40,"area":null},{"id":"2506.01048","title":"IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory","created":"2025-06-01","cited_by_count":40,"area":null},{"id":"2506.20380","title":"TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis","created":"2025-06-25","cited_by_count":39,"area":null},{"id":"2204.04516","title":"Uncertainty-Informed Deep Learning Models Enable High-Confidence Predictions for Digital Histopathology","created":"2022-04-09","cited_by_count":37,"area":null},{"id":"2106.07032","title":"Category Theory in Machine Learning","created":"2021-06-13","cited_by_count":36,"area":null},{"id":"2209.10526","title":"Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces","created":"2022-09-21","cited_by_count":36,"area":null},{"id":"2402.03659","title":"Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models","created":"2024-02-06","cited_by_count":36,"area":null},{"id":"2406.14673","title":"Insights into LLM Long-Context Failures: When Transformers Know but Don't Tell","created":"2024-06-20","cited_by_count":36,"area":null},{"id":"2107.11889","title":"GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks","created":"2021-07-25","cited_by_count":35,"area":null},{"id":"2204.09874","title":"Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics","created":"2022-04-21","cited_by_count":35,"area":null},{"id":"2401.11969","title":"Claim Detection for Automated Fact-checking: A Survey on Monolingual, Multilingual and Cross-Lingual Research","created":"2024-01-22","cited_by_count":35,"area":null},{"id":"2102.09099","title":"NuCLS: A scalable crowdsourcing, deep learning approach and dataset for nucleus classification, localization and segmentation","created":"2021-02-18","cited_by_count":34,"area":null},{"id":"2305.19753","title":"The Tunnel Effect: Building Data Representations in Deep Neural Networks","created":"2023-05-31","cited_by_count":34,"area":null},{"id":"2311.01479","title":"Detecting Out-of-Distribution Through the Lens of Neural Collapse","created":"2023-11-02","cited_by_count":34,"area":null},{"id":"2402.15343","title":"NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data","created":"2024-02-23","cited_by_count":34,"area":null},{"id":"2406.13469","title":"Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks","created":"2024-06-19","cited_by_count":34,"area":null},{"id":"2205.12551","title":"Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers","created":"2022-05-25","cited_by_count":33,"area":null},{"id":"2207.04043","title":"The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications","created":"2022-07-08","cited_by_count":33,"area":null},{"id":"2103.14608","title":"On UMAP's true loss function","created":"2021-03-26","cited_by_count":32,"area":null},{"id":"2110.15278","title":"Self-supervised EEG Representation Learning for Automatic Sleep Staging","created":"2021-10-27","cited_by_count":32,"area":null},{"id":"2202.07001","title":"Handcrafted Histological Transformer (H2T): Unsupervised Representation of Whole Slide Images","created":"2022-02-14","cited_by_count":32,"area":null},{"id":"2305.14321","title":"ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings","created":"2023-05-23","cited_by_count":32,"area":null},{"id":"2311.09090","title":"Social Bias Probing: Fairness Benchmarking for Language Models","created":"2023-11-15","cited_by_count":32,"area":null},{"id":"2209.07695","title":"Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation","created":"2022-09-16","cited_by_count":31,"area":null},{"id":"2212.11854","title":"Data-Centric Artificial Intelligence","created":"2022-12-22","cited_by_count":31,"area":null}],"next_cursor":"100"}