{"list":"other","total":90,"rows":[{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"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":"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":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"2410.07864","title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","created":"2024-10-10","cited_by_count":691},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2403.14624","title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","created":"2024-03-21","cited_by_count":586},{"id":"2112.03227","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","created":"2021-12-06","cited_by_count":584},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"id":"2505.06111","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","created":"2025-05-09","cited_by_count":410},{"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":"2401.02117","title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","created":"2024-01-04","cited_by_count":391},{"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":"2410.11758","title":"Latent Action Pretraining from Videos","created":"2024-10-15","cited_by_count":321},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304},{"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":"2410.06158","title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","created":"2024-10-08","cited_by_count":296},{"id":"2412.14803","title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","created":"2024-12-19","cited_by_count":289},{"id":"2109.13396","title":"Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets","created":"2021-09-27","cited_by_count":250},{"id":"2210.03109","title":"Real-World Robot Learning with Masked Visual Pre-training","created":"2022-10-06","cited_by_count":245},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226},{"id":"2210.06407","title":"Interactive Language: Talking to Robots in Real Time","created":"2022-10-12","cited_by_count":218},{"id":"2503.00200","title":"Unified Video Action Model","created":"2025-02-28","cited_by_count":205},{"id":"2508.07917","title":"MolmoAct: Action Reasoning Models that can Reason in Space","created":"2025-08-11","cited_by_count":197},{"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":"2412.13877","title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","created":"2024-12-18","cited_by_count":175},{"id":"2309.01918","title":"RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking","created":"2023-09-05","cited_by_count":169},{"id":"2403.03181","title":"Behavior Generation with Latent Actions","created":"2024-03-05","cited_by_count":160},{"id":"2112.01511","title":"The Surprising Effectiveness of Representation Learning for Visual Imitation","created":"2021-12-02","cited_by_count":154},{"id":"2409.20537","title":"Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers","created":"2024-09-30","cited_by_count":148},{"id":"2308.10901","title":"Structured World Models from Human Videos","created":"2023-08-21","cited_by_count":147},{"id":"2210.11339","title":"VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors","created":"2022-10-20","cited_by_count":136},{"id":"2305.12821","title":"FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation","created":"2023-05-22","cited_by_count":133},{"id":"2104.05859","title":"Rapid Exploration for Open-World Navigation with Latent Goal Models","created":"2021-04-12","cited_by_count":121},{"id":"2507.15493","title":"GR-3 Technical Report","created":"2025-07-21","cited_by_count":111},{"id":"2211.08416","title":"Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment","created":"2022-11-15","cited_by_count":108},{"id":"2210.10047","title":"From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data","created":"2022-10-18","cited_by_count":103},{"id":"2210.01911","title":"Grounding Language with Visual Affordances over Unstructured Data","created":"2022-10-04","cited_by_count":101},{"id":"2311.16098","title":"On Bringing Robots Home","created":"2023-11-27","cited_by_count":101},{"id":"2109.13841","title":"Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation","created":"2021-09-28","cited_by_count":83},{"id":"2501.10105","title":"Universal Actions for Enhanced Embodied Foundation Models","created":"2025-01-17","cited_by_count":82},{"id":"2209.08959","title":"Latent Plans for Task-Agnostic Offline Reinforcement Learning","created":"2022-09-19","cited_by_count":81},{"id":"2401.08553","title":"FMB: a Functional Manipulation Benchmark for Generalizable Robotic Learning","created":"2024-01-16","cited_by_count":80},{"id":"1709.10489","title":"Self-supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation","created":"2017-09-29","cited_by_count":77},{"id":"2210.11435","title":"Learning and Retrieval from Prior Data for Skill-based Imitation Learning","created":"2022-10-20","cited_by_count":77},{"id":"2507.17520","title":"InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulation","created":"2025-07-23","cited_by_count":72},{"id":"2309.14320","title":"MUTEX: Learning Unified Policies from Multimodal Task Specifications","created":"2023-09-25","cited_by_count":70},{"id":"2206.15469","title":"Watch and Match: Supercharging Imitation with Regularized Optimal Transport","created":"2022-06-30","cited_by_count":67},{"id":"2306.01874","title":"SACSoN: Scalable Autonomous Control for Social Navigation","created":"2023-06-02","cited_by_count":61},{"id":"2307.08927","title":"Multi-Stage Cable Routing through Hierarchical Imitation Learning","created":"2023-07-18","cited_by_count":60},{"id":"2306.17237","title":"HYDRA: Hybrid Robot Actions for Imitation Learning","created":"2023-06-29","cited_by_count":55},{"id":"2407.15840","title":"QueST: Self-Supervised Skill Abstractions for Learning Continuous Control","created":"2024-07-22","cited_by_count":53},{"id":"2306.10007","title":"Robot Learning with Sensorimotor Pre-training","created":"2023-06-16","cited_by_count":51},{"id":"2312.04549","title":"PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play","created":"2023-12-07","cited_by_count":50},{"id":"2306.00942","title":"Train Offline, Test Online: A Real Robot Learning Benchmark","created":"2023-06-01","cited_by_count":47},{"id":"2306.04632","title":"Designing a Better Asymmetric VQGAN for StableDiffusion","created":"2023-06-07","cited_by_count":45},{"id":"2310.16029","title":"Finetuning Offline World Models in the Real World","created":"2023-10-24","cited_by_count":41},{"id":"2402.14407","title":"Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training","created":"2024-02-22","cited_by_count":26},{"id":"2504.16925","title":"Latent Diffusion Planning for Imitation Learning","created":"2025-04-23","cited_by_count":26},{"id":"2409.07163","title":"Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models","created":"2024-09-11","cited_by_count":23},{"id":"2506.14608","title":"Latent Action Diffusion for Cross-Embodiment Manipulation","created":"2025-06-17","cited_by_count":20},{"id":"2509.02055","title":"Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance","created":"2025-09-02","cited_by_count":20},{"id":"2409.18707","title":"Discrete Policy: Learning Disentangled Action Space for Multi-Task Robotic Manipulation","created":"2024-09-27","cited_by_count":19},{"id":"2503.13217","title":"Dense Policy: Bidirectional Autoregressive Learning of Actions","created":"2025-03-17","cited_by_count":19},{"id":"2502.10040","title":"Diffusion Trajectory-guided Policy for Long-horizon Robot Manipulation","created":"2025-02-14","cited_by_count":15},{"id":"2506.03574","title":"SwitchVLA: Execution-Aware Task Switching for Vision-Language-Action Models","created":"2025-06-04","cited_by_count":15},{"id":"2107.05842","title":"Motion Planning by Learning the Solution Manifold in Trajectory Optimization","created":"2021-07-13","cited_by_count":13},{"id":"2212.04573","title":"Modularity through Attention: Efficient Training and Transfer of Language-Conditioned Policies for Robot Manipulation","created":"2022-12-08","cited_by_count":12},{"id":"2309.02754","title":"Pre- and post-contact policy decomposition for non-prehensile manipulation with zero-shot sim-to-real transfer","created":"2023-09-06","cited_by_count":12}],"next_cursor":null}