{"list":"other","total":55,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1910.09457","title":"Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods","created":"2019-10-21","cited_by_count":913},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"1906.03671","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","created":"2019-06-09","cited_by_count":610},{"id":"2506.01844","title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","created":"2025-06-02","cited_by_count":530},{"id":"1810.09136","title":"Do Deep Generative Models Know What They Don't Know?","created":"2018-10-22","cited_by_count":443},{"id":"1906.08158","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","created":"2019-06-19","cited_by_count":432},{"id":"2503.06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","created":"2025-03-09","cited_by_count":405},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"2603.16666","title":"Fast-WAM: Do World Action Models Need Test-time Future Imagination?","created":"2026-03-17","cited_by_count":349},{"id":"2307.01928","title":"Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners","created":"2023-07-04","cited_by_count":308},{"id":"2510.10274","title":"X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model","created":"2025-10-11","cited_by_count":303},{"id":"2601.16163","title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","created":"2026-01-22","cited_by_count":300},{"id":"2403.04696","title":"Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification","created":"2024-03-07","cited_by_count":162},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142},{"id":"2410.00371","title":"AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation","created":"2024-10-01","cited_by_count":125},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121},{"id":"1907.06890","title":"A General Framework for Uncertainty Estimation in Deep Learning","created":"2019-07-16","cited_by_count":119},{"id":"2602.22818","title":"LeRobot: An Open-Source Library for End-to-End Robot Learning","created":"2026-02-26","cited_by_count":73},{"id":"2410.04640","title":"Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress","created":"2024-10-06","cited_by_count":69},{"id":"2402.03478","title":"Estimating Epistemic and Aleatoric Uncertainty with a Single Model","created":"2024-02-05","cited_by_count":54},{"id":"2503.08558","title":"Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies","created":"2025-03-11","cited_by_count":52},{"id":"2605.02881","title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","created":"2026-05-04","cited_by_count":50},{"id":"2203.09410","title":"A Framework and Benchmark for Deep Batch Active Learning for Regression","created":"2022-03-17","cited_by_count":49},{"id":"2402.10189","title":"Uncertainty Quantification for In-Context Learning of Large Language Models","created":"2024-02-15","cited_by_count":45},{"id":"2510.09459","title":"Failure Prediction at Runtime for Generative Robot Policies","created":"2025-10-10","cited_by_count":42},{"id":"2502.08623","title":"Robot Data Curation with Mutual Information Estimators","created":"2025-02-12","cited_by_count":37},{"id":"2410.14868","title":"Diff-DAgger: Uncertainty Estimation with Diffusion Policy for Robotic Manipulation","created":"2024-10-18","cited_by_count":33},{"id":"2502.00290","title":"Estimating LLM Uncertainty with Evidence","created":"2025-02-01","cited_by_count":26},{"id":"2502.20946","title":"Generative Uncertainty in Diffusion Models","created":"2025-02-28","cited_by_count":23},{"id":"2506.19121","title":"CUPID: Curating Data your Robot Loves with Influence Functions","created":"2025-06-23","cited_by_count":23},{"id":"2406.18580","title":"Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models","created":"2024-06-05","cited_by_count":22},{"id":"2411.01293","title":"Diffusion Models as Cartoonists: The Curious Case of High Density Regions","created":"2024-11-02","cited_by_count":21},{"id":"1905.02780","title":"Uncertainty-Aware Data Aggregation for Deep Imitation Learning","created":"2019-05-07","cited_by_count":20},{"id":"2512.05927","title":"World Models That Know When They Don't Know - Controllable Video Generation with Calibrated Uncertainty","created":"2025-12-05","cited_by_count":17},{"id":"2601.09512","title":"CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion","created":"2026-01-14","cited_by_count":17},{"id":"2604.23775","title":"Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms","created":"2026-04-26","cited_by_count":13},{"id":"2412.03178","title":"Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation","created":"2024-12-04","cited_by_count":11},{"id":"2410.05026","title":"Active Fine-Tuning of Multi-Task Policies","created":"2024-10-07","cited_by_count":9},{"id":"2503.01876","title":"Uncertainty Comes for Free: Human-in-the-Loop Policies with Diffusion Models","created":"2025-02-26","cited_by_count":8},{"id":"2601.21662","title":"Epistemic Uncertainty Quantification for Pre-trained VLMs via Riemannian Flow Matching","created":"2026-01-29","cited_by_count":2}],"next_cursor":null}