{"list":"other","total":103,"rows":[{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"id":"2303.01469","title":"Consistency Models","created":"2023-03-02","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2211.01095","title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","created":"2022-11-02","cited_by_count":938},{"id":"2007.11898","title":"ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM","created":"2020-07-23","cited_by_count":878},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2202.09778","title":"Pseudo Numerical Methods for Diffusion Models on Manifolds","created":"2022-02-20","cited_by_count":700},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"2405.14867","title":"Improved Distribution Matching Distillation for Fast Image Synthesis","created":"2024-05-23","cited_by_count":684},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625},{"id":"2505.13447","title":"Mean Flows for One-step Generative Modeling","created":"2025-05-19","cited_by_count":561},{"id":"2204.13902","title":"Fast Sampling of Diffusion Models with Exponential Integrator","created":"2022-04-29","cited_by_count":532},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2310.02279","title":"Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion","created":"2023-10-01","cited_by_count":459},{"id":"2302.04867","title":"UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models","created":"2023-02-09","cited_by_count":450},{"id":"2412.07772","title":"From Slow Bidirectional to Fast Autoregressive Video Diffusion Models","created":"2024-12-10","cited_by_count":433},{"id":"1708.03852","title":"VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator","created":"2017-08-13","cited_by_count":423},{"id":"2409.02048","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","created":"2024-09-03","cited_by_count":403},{"id":"2410.12557","title":"One Step Diffusion via Shortcut Models","created":"2024-10-16","cited_by_count":391},{"id":"2312.00858","title":"DeepCache: Accelerating Diffusion Models for Free","created":"2023-12-01","cited_by_count":359},{"id":"2106.02634","title":"Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering","created":"2021-06-04","cited_by_count":332},{"id":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"id":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","cited_by_count":287},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"2411.19108","title":"Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model","created":"2024-11-28","cited_by_count":269},{"id":"2509.22622","title":"LongLive: Real-time Interactive Long Video Generation","created":"2025-09-26","cited_by_count":265},{"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":"2509.25161","title":"Rolling Forcing: Autoregressive Long Video Diffusion in Real Time","created":"2025-09-29","cited_by_count":234},{"id":"2303.17604","title":"Token Merging for Fast Stable Diffusion","created":"2023-03-30","cited_by_count":224},{"id":"2406.09394","title":"WonderWorld: Interactive 3D Scene Generation from a Single Image","created":"2024-06-13","cited_by_count":202},{"id":"2510.02283","title":"Self-Forcing++: Towards Minute-Scale High-Quality Video Generation","created":"2025-10-02","cited_by_count":192},{"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":"2311.16933","title":"SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models","created":"2023-11-28","cited_by_count":175},{"id":"2504.12369","title":"WorldMem: Long-term Consistent World Simulation with Memory","created":"2025-04-16","cited_by_count":168},{"id":"2506.03141","title":"Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval","created":"2025-06-03","cited_by_count":163},{"id":"2310.13268","title":"DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics","created":"2023-10-20","cited_by_count":161},{"id":"2403.07420","title":"DragAnything: Motion Control for Anything using Entity Representation","created":"2024-03-12","cited_by_count":159},{"id":"2312.03884","title":"WonderJourney: Going from Anywhere to Everywhere","created":"2023-12-06","cited_by_count":158},{"id":"2501.08316","title":"Diffusion Adversarial Post-Training for One-Step Video Generation","created":"2025-01-14","cited_by_count":151},{"id":"2407.01425","title":"FORA: Fast-Forward Caching in Diffusion Transformer Acceleration","created":"2024-07-01","cited_by_count":137},{"id":"2312.01026","title":"Token Fusion: Bridging the Gap between Token Pruning and Token Merging","created":"2023-12-02","cited_by_count":125},{"id":"2410.15957","title":"CamI2V: Camera-Controlled Image-to-Video Diffusion Model","created":"2024-10-21","cited_by_count":120},{"id":"2312.10656","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","created":"2023-12-17","cited_by_count":113},{"id":"2504.08388","title":"MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft","created":"2025-04-11","cited_by_count":97},{"id":"2508.21058","title":"Mixture of Contexts for Long Video Generation","created":"2025-08-28","cited_by_count":95},{"id":"2412.07760","title":"SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints","created":"2024-12-10","cited_by_count":93},{"id":"2506.09350","title":"Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation","created":"2025-06-11","cited_by_count":90},{"id":"2312.00094","title":"Fast ODE-based Sampling for Diffusion Models in Around 5 Steps","created":"2023-11-30","cited_by_count":84},{"id":"2506.19852","title":"Radial Attention: $O(n\\log n)$ Sparse Attention with Energy Decay for Long Video Generation","created":"2025-06-24","cited_by_count":69},{"id":"2405.17933","title":"ToonCrafter: Generative Cartoon Interpolation","created":"2024-05-28","cited_by_count":68},{"id":"2411.04989","title":"SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation","created":"2024-11-07","cited_by_count":68},{"id":"2503.18860","title":"HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation","created":"2025-03-24","cited_by_count":59},{"id":"2011.10687","title":"HDR Environment Map Estimation for Real-Time Augmented Reality","created":"2020-11-21","cited_by_count":47},{"id":"2311.17261","title":"SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors","created":"2023-11-28","cited_by_count":43},{"id":"2312.02216","title":"DragVideo: Interactive Drag-style Video Editing","created":"2023-12-03","cited_by_count":40},{"id":"2506.15673","title":"UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting","created":"2025-06-18","cited_by_count":40},{"id":"2502.04847","title":"HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation","created":"2025-02-07","cited_by_count":39},{"id":"2405.05252","title":"Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models","created":"2024-05-08","cited_by_count":38},{"id":"2406.10981","title":"ViD-GPT: Introducing GPT-style Autoregressive Generation in Video Diffusion Models","created":"2024-06-16","cited_by_count":36},{"id":"2403.05659","title":"Audio-Synchronized Visual Animation","created":"2024-03-08","cited_by_count":32},{"id":"2501.12389","title":"Taming Teacher Forcing for Masked Autoregressive Video Generation","created":"2025-01-21","cited_by_count":30},{"id":"2510.01784","title":"Pack and Force Your Memory: Long-form and Consistent Video Generation","created":"2025-10-02","cited_by_count":29},{"id":"2410.16668","title":"Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling","created":"2024-10-22","cited_by_count":25},{"id":"2305.17098","title":"ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond","created":"2023-05-26","cited_by_count":22},{"id":"2412.15191","title":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation","created":"2024-12-19","cited_by_count":22},{"id":"2508.03694","title":"LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation","created":"2025-08-05","cited_by_count":22},{"id":"2008.07817","title":"Retargetable AR: Context-aware Augmented Reality in Indoor Scenes based on 3D Scene Graph","created":"2020-08-18","cited_by_count":19},{"id":"2507.12952","title":"LoViC: Efficient Long Video Generation with Context Compression","created":"2025-07-17","cited_by_count":19},{"id":"2504.02542","title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation","created":"2025-04-03","cited_by_count":17},{"id":"2505.11707","title":"Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration","created":"2025-05-16","cited_by_count":17},{"id":"2312.09767","title":"DreamTalk: When Emotional Talking Head Generation Meets Diffusion Probabilistic Models","created":"2023-12-15","cited_by_count":16},{"id":"2503.23284","title":"SketchVideo: Sketch-based Video Generation and Editing","created":"2025-03-30","cited_by_count":16},{"id":"2502.17414","title":"X-Dancer: Expressive Music to Human Dance Video Generation","created":"2025-02-24","cited_by_count":15},{"id":"2405.09266","title":"Dance Any Beat: Blending Beats with Visuals in Dance Video Generation","created":"2024-05-15","cited_by_count":14},{"id":"2406.02461","title":"RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpainting","created":"2024-06-04","cited_by_count":14},{"id":"2502.11515","title":"SayAnything: Audio-Driven Lip Synchronization with Conditional Video Diffusion","created":"2025-02-17","cited_by_count":12},{"id":"2508.06082","title":"SwiftVideo: A Unified Framework for Few-Step Video Generation through Trajectory-Distribution Alignment","created":"2025-08-08","cited_by_count":10},{"id":"2310.15072","title":"RD-VIO: Robust Visual-Inertial Odometry for Mobile Augmented Reality in Dynamic Environments","created":"2023-10-23","cited_by_count":9},{"id":"2502.10190","title":"VideoDiff: Human-AI Video Co-Creation with Alternatives","created":"2025-02-14","cited_by_count":8},{"id":"2504.21360","title":"ImaginateAR: AI-Assisted In-Situ Authoring in Augmented Reality","created":"2025-04-30","cited_by_count":8},{"id":"2304.11842","title":"Gen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Design","created":"2023-04-24","cited_by_count":7},{"id":"2503.03134","title":"Making AI-Enhanced Videos: Analyzing Generative AI Use Cases in YouTube Content Creation","created":"2025-03-05","cited_by_count":6},{"id":"2405.07089","title":"SonifyAR: Context-Aware Sound Generation in Augmented Reality","created":"2024-05-11","cited_by_count":5},{"id":"2510.03550","title":"Streaming Drag-Oriented Interactive Video Manipulation: Drag Anything, Anytime!","created":"2025-10-03","cited_by_count":5},{"id":"2310.14437","title":"Mobile AR Depth Estimation: Challenges & Prospects -- Extended Version","created":"2023-10-22","cited_by_count":3},{"id":"2409.13926","title":"SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending","created":"2024-09-20","cited_by_count":3},{"id":"2410.10821","title":"Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion Models","created":"2024-10-14","cited_by_count":3},{"id":"2501.16557","title":"CARING-AI: Towards Authoring Context-aware Augmented Reality INstruction through Generative Artificial Intelligence","created":"2025-01-27","cited_by_count":3},{"id":"2502.15604","title":"Cross-Format Retrieval-Augmented Generation in XR with LLMs for Context-Aware Maintenance Assistance","created":"2025-02-21","cited_by_count":3},{"id":"2508.15169","title":"MeSS: City Mesh-Guided Outdoor Scene Generation with Cross-View Consistent Diffusion","created":"2025-08-21","cited_by_count":3},{"id":"2207.00798","title":"Arigat\\=o: Effects of Adaptive Guidance on Engagement and Performance in Augmented Reality Learning Environments","created":"2022-07-02","cited_by_count":2},{"id":"2502.20944","title":"AR You on Track? Investigating Effects of Augmented Reality Anchoring on Dual-Task Performance While Walking","created":"2025-02-28","cited_by_count":2}],"next_cursor":"100"}