{"total":2898,"rows":[{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184,"area":"alignment"},{"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":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"area":"alignment"},{"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":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729,"area":"alignment"},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553,"area":"mechinterp"},{"id":"2401.18059","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","created":"2024-01-31","cited_by_count":532,"area":"rag"},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2210.14896","title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","created":"2022-10-26","cited_by_count":379,"area":"diffusion"},{"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":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261,"area":"alignment"},{"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":"2305.18274","title":"Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors","created":"2023-05-29","cited_by_count":160,"area":"diffusion"},{"id":"2204.09179","title":"On the Representation Collapse of Sparse Mixture of Experts","created":"2022-04-20","cited_by_count":157,"area":"moe"},{"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":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144,"area":"alignment"},{"id":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139,"area":null},{"id":"2312.11752","title":"Learning a Diffusion Model Policy from Rewards via Q-Score Matching","created":"2023-12-18","cited_by_count":138,"area":"diffusion"},{"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":"2312.10812","title":"Learning to Act without Actions","created":"2023-12-17","cited_by_count":121,"area":"wm"},{"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":"2209.15611","title":"Protein structure generation via folding diffusion","created":"2022-09-30","cited_by_count":115,"area":"diffusion"},{"id":"2503.18938","title":"AdaWorld: Learning Adaptable World Models with Latent Actions","created":"2025-03-24","cited_by_count":114,"area":"wm"},{"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":"2502.03444","title":"Masked Autoencoders Are Effective Tokenizers for Diffusion Models","created":"2025-02-05","cited_by_count":96,"area":"diffusion"},{"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":"2502.13124","title":"NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions","created":"2025-02-18","cited_by_count":84,"area":"lr"},{"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":"2303.11313","title":"CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition","created":"2023-03-20","cited_by_count":77,"area":"mllm"},{"id":"2210.01189","title":"Rank-N-Contrast: Learning Continuous Representations for Regression","created":"2022-10-03","cited_by_count":76,"area":null},{"id":"2412.03556","title":"Best-of-N Jailbreaking","created":"2024-12-04","cited_by_count":76,"area":"safety"},{"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":"2510.01179","title":"TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments","created":"2025-10-01","cited_by_count":69,"area":"agents"},{"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":"2404.07983","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models","created":"2024-04-11","cited_by_count":57,"area":"mllm"},{"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":"2505.20347","title":"SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data","created":"2025-05-25","cited_by_count":51,"area":"lr"},{"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":"2601.05230","title":"Learning Latent Action World Models In The Wild","created":"2026-01-08","cited_by_count":47,"area":"wm"},{"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":"2506.08745","title":"Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning","created":"2025-06-10","cited_by_count":46,"area":"lr"},{"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":"2505.23762","title":"ZeroGUI: Automating Online GUI Learning at Zero Human Cost","created":"2025-05-29","cited_by_count":44,"area":"mllm"},{"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}],"next_cursor":"100"}