{"list":"other","total":62,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"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":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"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":"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":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"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":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"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":"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":"2411.04983","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","created":"2024-11-07","cited_by_count":386},{"id":"2407.12772","title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","created":"2024-07-17","cited_by_count":353},{"id":"2412.14803","title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","created":"2024-12-19","cited_by_count":289},{"id":"2310.19785","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","created":"2023-10-30","cited_by_count":254},{"id":"2406.10721","title":"RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics","created":"2024-06-15","cited_by_count":251},{"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":"2507.16815","title":"ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning","created":"2025-07-22","cited_by_count":156},{"id":"2512.15692","title":"mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs","created":"2025-12-17","cited_by_count":142},{"id":"2601.10611","title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","created":"2026-01-15","cited_by_count":139},{"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":"2508.05635","title":"Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation","created":"2025-08-07","cited_by_count":137},{"id":"2511.04670","title":"Cambrian-S: Towards Spatial Supersensing in Video","created":"2025-11-06","cited_by_count":134},{"id":"2505.21500","title":"ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models","created":"2025-05-27","cited_by_count":118},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115},{"id":"2406.09418","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","created":"2024-06-13","cited_by_count":115},{"id":"2508.00795","title":"Video Generators are Robot Policies","created":"2025-08-01","cited_by_count":92},{"id":"2509.00576","title":"Galaxea Open-World Dataset and G0 Dual-System VLA Model","created":"2025-08-30","cited_by_count":92},{"id":"2312.06722","title":"EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning","created":"2023-12-11","cited_by_count":69},{"id":"2512.06963","title":"VideoVLA: Video Generators Can Be Generalizable Robot Manipulators","created":"2025-12-07","cited_by_count":64},{"id":"2507.12898","title":"Vidar: Embodied Video Diffusion Model for Generalist Manipulation","created":"2025-07-17","cited_by_count":62},{"id":"2510.17269","title":"FineVision: Open Data Is All You Need","created":"2025-10-20","cited_by_count":53},{"id":"2602.12215","title":"LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion","created":"2026-02-12","cited_by_count":52},{"id":"2412.11974","title":"Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning","created":"2024-12-16","cited_by_count":47},{"id":"2506.16211","title":"ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models","created":"2025-06-19","cited_by_count":43},{"id":"2512.22414","title":"Emergence of Human to Robot Transfer in Vision-Language-Action Models","created":"2025-12-27","cited_by_count":42},{"id":"2505.15517","title":"Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets","created":"2025-05-21","cited_by_count":40},{"id":"2601.14352","title":"RoboBrain 2.5: Depth in Sight, Time in Mind","created":"2026-01-20","cited_by_count":39},{"id":"2509.25162","title":"AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models","created":"2025-09-29","cited_by_count":36},{"id":"2505.08548","title":"From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation","created":"2025-05-13","cited_by_count":35},{"id":"2602.14979","title":"RynnBrain: Open Embodied Foundation Models","created":"2026-02-13","cited_by_count":35},{"id":"2601.04061","title":"CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos","created":"2026-01-07","cited_by_count":31},{"id":"2602.03310","title":"RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization","created":"2026-02-03","cited_by_count":30},{"id":"2512.13687","title":"Towards Scalable Pre-training of Visual Tokenizers for Generation","created":"2025-12-15","cited_by_count":28},{"id":"2512.04952","title":"FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization","created":"2025-12-04","cited_by_count":22},{"id":"2510.01954","title":"Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs","created":"2025-10-02","cited_by_count":20},{"id":"2510.23569","title":"EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT","created":"2025-10-27","cited_by_count":16},{"id":"2507.17141","title":"Towards Human-level Intelligence via Human-like Whole-Body Manipulation","created":"2025-07-23","cited_by_count":13},{"id":"2604.11689","title":"LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment","created":"2026-04-13","cited_by_count":12},{"id":"2505.12312","title":"Visuospatial Cognitive Assistant","created":"2025-05-18","cited_by_count":11},{"id":"2604.19734","title":"UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling","created":"2026-04-21","cited_by_count":10},{"id":"2501.14622","title":"ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning","created":"2025-01-24","cited_by_count":8},{"id":"2512.08580","title":"Mind to Hand: Purposeful Robotic Control via Embodied Reasoning","created":"2025-12-09","cited_by_count":8}],"next_cursor":null}