{"list":"other","total":53,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"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":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211},{"id":"2108.05877","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","created":"2021-08-12","cited_by_count":206},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2412.02700","title":"Motion Prompting: Controlling Video Generation with Motion Trajectories","created":"2024-12-03","cited_by_count":178},{"id":"2407.21705","title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation","created":"2024-07-31","cited_by_count":164},{"id":"2511.18870","title":"HunyuanVideo 1.5 Technical Report","created":"2025-11-24","cited_by_count":160},{"id":"2403.07420","title":"DragAnything: Motion Control for Anything using Entity Representation","created":"2024-03-12","cited_by_count":159},{"id":"2509.24527","title":"Training Agents Inside of Scalable World Models","created":"2025-09-29","cited_by_count":136},{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124},{"id":"2501.08331","title":"Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise","created":"2025-01-14","cited_by_count":117},{"id":"2401.00896","title":"TrailBlazer: Trajectory Control for Diffusion-Based Video Generation","created":"2023-12-31","cited_by_count":91},{"id":"2411.19548","title":"ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration","created":"2024-11-29","cited_by_count":89},{"id":"2312.07509","title":"PEEKABOO: Interactive Video Generation via Masked-Diffusion","created":"2023-12-12","cited_by_count":76},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","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":"2411.19324","title":"Trajectory Attention for Fine-grained Video Motion Control","created":"2024-11-28","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":"2506.22355","title":"Embodied AI Agents: Modeling the World","created":"2025-06-27","cited_by_count":61},{"id":"2406.16863","title":"FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models","created":"2024-06-24","cited_by_count":56},{"id":"2502.04299","title":"MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation","created":"2025-02-06","cited_by_count":50},{"id":"2512.08765","title":"Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance","created":"2025-12-09","cited_by_count":45},{"id":"2505.22944","title":"ATI: Any Trajectory Instruction for Controllable Video Generation","created":"2025-05-28","cited_by_count":43},{"id":"2408.11475","title":"TrackGo: A Flexible and Efficient Method for Controllable Video Generation","created":"2024-08-21","cited_by_count":39},{"id":"2509.15212","title":"RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation","created":"2025-09-18","cited_by_count":25},{"id":"2510.08807","title":"Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation","created":"2025-10-09","cited_by_count":25},{"id":"2512.02015","title":"Generative Video Motion Editing with 3D Point Tracks","created":"2025-12-01","cited_by_count":23},{"id":"2602.10106","title":"EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration","created":"2026-02-10","cited_by_count":21},{"id":"2506.09995","title":"PlayerOne: Egocentric World Simulator","created":"2025-06-11","cited_by_count":20},{"id":"2503.24026","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","created":"2025-03-31","cited_by_count":19},{"id":"2508.13104","title":"Precise Action-to-Video Generation Through Visual Action Prompts","created":"2025-08-18","cited_by_count":15},{"id":"2508.06080","title":"DreamVE: Unified Instruction-based Image and Video Editing","created":"2025-08-08","cited_by_count":11},{"id":"2510.03135","title":"Mask2IV: Interaction-Centric Video Generation via Mask Trajectories","created":"2025-10-03","cited_by_count":10},{"id":"2511.18173","title":"EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses","created":"2025-11-22","cited_by_count":8},{"id":"2506.09384","title":"Analyzing Key Objectives in Human-to-Robot Retargeting for Dexterous Manipulation","created":"2025-06-11","cited_by_count":6},{"id":"2409.19911","title":"Replace Anyone in Videos","created":"2024-09-30","cited_by_count":4},{"id":"2508.19852","title":"Ego-centric Predictive Model Conditioned on Hand Trajectories","created":"2025-08-27","cited_by_count":4},{"id":"2512.09646","title":"VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification","created":"2025-12-10","cited_by_count":4}],"next_cursor":null}