{"list":"other","total":60,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"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":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"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":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299},{"id":"2310.10639","title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","created":"2023-10-16","cited_by_count":269},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228},{"id":"2004.15021","title":"Consistent Video Depth Estimation","created":"2020-04-30","cited_by_count":220},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2212.08333","title":"AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains","created":"2022-12-16","cited_by_count":208},{"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":"2310.08576","title":"Learning to Act from Actionless Videos through Dense Correspondences","created":"2023-10-12","cited_by_count":164},{"id":"2303.00905","title":"Open-World Object Manipulation using Pre-trained Vision-Language Models","created":"2023-03-02","cited_by_count":156},{"id":"2409.16283","title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","created":"2024-09-24","cited_by_count":153},{"id":"2407.15208","title":"Flow as the Cross-Domain Manipulation Interface","created":"2024-07-21","cited_by_count":132},{"id":"2507.05331","title":"A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation","created":"2025-07-07","cited_by_count":129},{"id":"2405.01527","title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","created":"2024-05-02","cited_by_count":124},{"id":"2309.08587","title":"Compositional Foundation Models for Hierarchical Planning","created":"2023-09-15","cited_by_count":95},{"id":"2508.00795","title":"Video Generators are Robot Policies","created":"2025-08-01","cited_by_count":92},{"id":"2205.04382","title":"FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objects","created":"2022-05-09","cited_by_count":91},{"id":"2406.16862","title":"Dreamitate: Real-World Visuomotor Policy Learning via Video Generation","created":"2024-06-24","cited_by_count":87},{"id":"2503.17973","title":"PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos","created":"2025-03-23","cited_by_count":87},{"id":"2401.11439","title":"General Flow as Foundation Affordance for Scalable Robot Learning","created":"2024-01-21","cited_by_count":85},{"id":"2504.14717","title":"TAPIP3D: Tracking Any Point in Persistent 3D Geometry","created":"2025-04-20","cited_by_count":69},{"id":"2407.07889","title":"AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulation","created":"2024-07-10","cited_by_count":54},{"id":"2312.00775","title":"Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Plans","created":"2023-12-01","cited_by_count":52},{"id":"2503.07135","title":"VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation","created":"2025-03-10","cited_by_count":46},{"id":"2507.00990","title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","created":"2025-07-01","cited_by_count":38},{"id":"2506.06199","title":"3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model","created":"2025-06-06","cited_by_count":37},{"id":"2306.12893","title":"FlowBot++: Learning Generalized Articulated Objects Manipulation via Articulation Projection","created":"2023-06-22","cited_by_count":34},{"id":"2503.23877","title":"ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos","created":"2025-03-31","cited_by_count":32},{"id":"2507.13097","title":"GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training","created":"2025-07-17","cited_by_count":32},{"id":"2505.03728","title":"PyRoki: A Modular Toolkit for Robot Kinematic Optimization","created":"2025-05-06","cited_by_count":30},{"id":"2312.06876","title":"Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks","created":"2023-12-11","cited_by_count":27},{"id":"2506.23126","title":"ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic Manipulation","created":"2025-06-29","cited_by_count":26},{"id":"2506.15680","title":"Particle-Grid Neural Dynamics for Learning Deformable Object Models from RGB-D Videos","created":"2025-06-18","cited_by_count":25},{"id":"2306.16700","title":"Dynamic-Resolution Model Learning for Object Pile Manipulation","created":"2023-06-29","cited_by_count":22},{"id":"2410.22332","title":"Local Policies Enable Zero-shot Long-horizon Manipulation","created":"2024-10-29","cited_by_count":22},{"id":"2406.11740","title":"Imagination Policy: Using Generative Point Cloud Models for Learning Manipulation Policies","created":"2024-06-17","cited_by_count":18},{"id":"2506.04227","title":"Object-centric 3D Motion Field for Robot Learning from Human Videos","created":"2025-06-04","cited_by_count":14},{"id":"2506.16652","title":"CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity","created":"2025-06-19","cited_by_count":8}],"next_cursor":null}