{"list":"other","total":52,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2502.19645","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","created":"2025-02-27","cited_by_count":883},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"2405.05941","title":"Evaluating Real-World Robot Manipulation Policies in Simulation","created":"2024-05-09","cited_by_count":495},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"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":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2308.08089","title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","created":"2023-08-16","cited_by_count":264},{"id":"2401.15977","title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","created":"2024-01-29","cited_by_count":211},{"id":"2501.03847","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control","created":"2025-01-07","cited_by_count":185},{"id":"2407.21705","title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation","created":"2024-07-31","cited_by_count":164},{"id":"2404.07987","title":"ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback","created":"2024-04-11","cited_by_count":154},{"id":"2307.00040","title":"DisCo: Disentangled Control for Realistic Human Dance Generation","created":"2023-06-30","cited_by_count":142},{"id":"2508.05635","title":"Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation","created":"2025-08-07","cited_by_count":137},{"id":"2405.11656","title":"URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images","created":"2024-05-19","cited_by_count":111},{"id":"2402.01566","title":"Boximator: Generating Rich and Controllable Motions for Video Synthesis","created":"2024-02-02","cited_by_count":107},{"id":"2506.07961","title":"BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models","created":"2025-06-09","cited_by_count":80},{"id":"2505.14357","title":"Vid2World: Crafting Video Diffusion Models to Interactive World Models","created":"2025-05-20","cited_by_count":76},{"id":"2502.08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","created":"2025-02-12","cited_by_count":74},{"id":"2412.07759","title":"3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation","created":"2024-12-10","cited_by_count":71},{"id":"2411.04989","title":"SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation","created":"2024-11-07","cited_by_count":68},{"id":"2406.15339","title":"Image Conductor: Precision Control for Interactive Video Synthesis","created":"2024-06-21","cited_by_count":63},{"id":"2503.16421","title":"MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance","created":"2025-03-20","cited_by_count":61},{"id":"2507.19468","title":"Back to the Features: DINO as a Foundation for Video World Models","created":"2025-07-25","cited_by_count":58},{"id":"2406.16863","title":"FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models","created":"2024-06-24","cited_by_count":56},{"id":"2502.07825","title":"Pre-Trained Video Generative Models as World Simulators","created":"2025-02-10","cited_by_count":44},{"id":"2506.09981","title":"ReSim: Reliable World Simulation for Autonomous Driving","created":"2025-06-11","cited_by_count":44},{"id":"2505.09723","title":"EnerVerse-AC: Envisioning Embodied Environments with Action Condition","created":"2025-05-14","cited_by_count":42},{"id":"2412.15214","title":"LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis","created":"2024-12-19","cited_by_count":39},{"id":"2506.21552","title":"Whole-Body Conditioned Egocentric Video Prediction","created":"2025-06-26","cited_by_count":30},{"id":"2011.02398","title":"A Modular Robotic Arm Control Stack for Research: Franka-Interface and FrankaPy","created":"2020-11-04","cited_by_count":25},{"id":"2502.04296","title":"Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression","created":"2025-02-06","cited_by_count":23},{"id":"2507.22885","title":"Viser: Imperative, Web-based 3D Visualization in Python","created":"2025-07-30","cited_by_count":23},{"id":"2409.10441","title":"CtRNet-X: Camera-to-Robot Pose Estimation in Real-world Conditions Using a Single Camera","created":"2024-09-16","cited_by_count":11},{"id":"2507.06224","title":"EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow","created":"2025-07-08","cited_by_count":11},{"id":"2512.16724","title":"VERM: Leveraging Foundation Models to Create a Virtual Eye for Efficient 3D Robotic Manipulation","created":"2025-12-18","cited_by_count":2}],"next_cursor":null}