{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"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":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"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":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"2405.05941","title":"Evaluating Real-World Robot Manipulation Policies in Simulation","created":"2024-05-09","cited_by_count":495},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2411.19650","title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","created":"2024-11-29","cited_by_count":422},{"id":"2503.09573","title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models","created":"2025-03-12","cited_by_count":409},{"id":"2311.01378","title":"Vision-Language Foundation Models as Effective Robot Imitators","created":"2023-11-02","cited_by_count":349},{"id":"2409.12514","title":"TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation","created":"2024-09-19","cited_by_count":339},{"id":"1811.03115","title":"Blockwise Parallel Decoding for Deep Autoregressive Models","created":"2018-11-07","cited_by_count":323},{"id":"2410.11758","title":"Latent Action Pretraining from Videos","created":"2024-10-15","cited_by_count":321},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"1910.10073","title":"Depth-Adaptive Transformer","created":"2019-10-22","cited_by_count":236},{"id":"2506.07339","title":"Real-Time Execution of Action Chunking Flow Policies","created":"2025-06-09","cited_by_count":216},{"id":"2502.06768","title":"Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions","created":"2025-02-10","cited_by_count":214},{"id":"1901.07821","title":"Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff","created":"2019-01-23","cited_by_count":211},{"id":"1802.06901","title":"Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement","created":"2018-02-19","cited_by_count":195},{"id":"2503.10631","title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","created":"2025-03-13","cited_by_count":181},{"id":"2107.05407","title":"PonderNet: Learning to Ponder","created":"2021-07-12","cited_by_count":168},{"id":"2403.03181","title":"Behavior Generation with Latent Actions","created":"2024-03-05","cited_by_count":160},{"id":"2505.23705","title":"Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better","created":"2025-05-29","cited_by_count":146},{"id":"2604.15483","title":"${\\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities","created":"2026-04-16","cited_by_count":138},{"id":"1812.05069","title":"Recent Advances in Autoencoder-Based Representation Learning","created":"2018-12-12","cited_by_count":133},{"id":"2306.11706","title":"RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation","created":"2023-06-20","cited_by_count":111},{"id":"2502.13967","title":"FlexTok: Resampling Images into 1D Token Sequences of Flexible Length","created":"2025-02-19","cited_by_count":110},{"id":"2507.01925","title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","created":"2025-07-02","cited_by_count":96},{"id":"2508.20072","title":"Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies","created":"2025-08-27","cited_by_count":90},{"id":"1402.0915","title":"Learning Ordered Representations with Nested Dropout","created":"2014-02-05","cited_by_count":84},{"id":"2603.04356","title":"RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots","created":"2026-03-04","cited_by_count":79},{"id":"2205.10337","title":"UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes","created":"2022-05-20","cited_by_count":78},{"id":"2403.19578","title":"Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics","created":"2024-03-28","cited_by_count":74},{"id":"2408.15980","title":"In-Context Imitation Learning via Next-Token Prediction","created":"2024-08-28","cited_by_count":70},{"id":"2507.01016","title":"VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers","created":"2025-07-01","cited_by_count":70},{"id":"2407.15840","title":"QueST: Self-Supervised Skill Abstractions for Learning Continuous Control","created":"2024-07-22","cited_by_count":53},{"id":"2503.08685","title":"\"Principal Components\" Enable A New Language of Images","created":"2025-03-11","cited_by_count":27},{"id":"2209.11133","title":"PACT: Perception-Action Causal Transformer for Autoregressive Robotics Pre-Training","created":"2022-09-22","cited_by_count":24},{"id":"2602.01067","title":"A Systematic Study of Data Modalities and Strategies for Co-training Large Behavior Models for Robot Manipulation","created":"2026-02-01","cited_by_count":22},{"id":"2602.15397","title":"ActionCodec: What Makes for Good Action Tokenizers","created":"2026-02-17","cited_by_count":18},{"id":"2507.09061","title":"Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control","created":"2025-07-11","cited_by_count":15},{"id":"2503.01206","title":"Action Tokenizer Matters in In-Context Imitation Learning","created":"2025-03-03","cited_by_count":14},{"id":"2509.23468","title":"Multi-Modal Manipulation via Multi-Modal Policy Consensus","created":"2025-09-27","cited_by_count":13},{"id":"2509.21983","title":"Hybrid Diffusion for Simultaneous Symbolic and Continuous Planning","created":"2025-09-26","cited_by_count":7},{"id":"2512.14697","title":"Spherical Leech Quantization for Visual Tokenization and Generation","created":"2025-12-16","cited_by_count":6},{"id":"2512.21898","title":"Flexible Multitask Learning with Factorized Diffusion Policy","created":"2025-12-26","cited_by_count":5}],"next_cursor":null}