{"list":"other","total":67,"rows":[{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2211.12194","title":"SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","created":"2022-11-22","cited_by_count":382},{"id":"2411.15098","title":"OminiControl: Minimal and Universal Control for Diffusion Transformer","created":"2024-11-22","cited_by_count":340},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"2307.15880","title":"Effective Whole-body Pose Estimation with Two-stages Distillation","created":"2023-07-29","cited_by_count":311},{"id":"2501.13918","title":"Improving Video Generation with Human Feedback","created":"2025-01-23","cited_by_count":284},{"id":"2309.14509","title":"DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models","created":"2023-09-25","cited_by_count":245},{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236},{"id":"2511.18870","title":"HunyuanVideo 1.5 Technical Report","created":"2025-11-24","cited_by_count":160},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158},{"id":"2311.16097","title":"CG-HOI: Contact-Guided 3D Human-Object Interaction Generation","created":"2023-11-27","cited_by_count":138},{"id":"2502.01061","title":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","created":"2025-02-03","cited_by_count":129},{"id":"2502.11079","title":"Phantom: Subject-consistent video generation via cross-modal alignment","created":"2025-02-16","cited_by_count":129},{"id":"2412.00733","title":"Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer","created":"2024-12-01","cited_by_count":122},{"id":"2409.02634","title":"Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency","created":"2024-09-04","cited_by_count":102},{"id":"2312.06553","title":"HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models","created":"2023-12-11","cited_by_count":93},{"id":"2503.08153","title":"WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation","created":"2025-03-11","cited_by_count":90},{"id":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87},{"id":"2506.18866","title":"OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation","created":"2025-06-23","cited_by_count":83},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83},{"id":"2512.13507","title":"Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model","created":"2025-12-15","cited_by_count":80},{"id":"2504.04842","title":"FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis","created":"2025-04-07","cited_by_count":77},{"id":"2309.05663","title":"Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips","created":"2023-09-11","cited_by_count":74},{"id":"2504.02436","title":"SkyReels-A2: Compose Anything in Video Diffusion Transformers","created":"2025-04-03","cited_by_count":73},{"id":"2505.20292","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","created":"2025-05-26","cited_by_count":73},{"id":"2411.10061","title":"EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation","created":"2024-11-15","cited_by_count":72},{"id":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69},{"id":"2505.22647","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","created":"2025-05-28","cited_by_count":66},{"id":"2412.09262","title":"LatentSync: Taming Audio-Conditioned Latent Diffusion Models for Lip Sync with SyncNet Supervision","created":"2024-12-12","cited_by_count":56},{"id":"2508.15761","title":"Waver: Wave Your Way to Lifelike Video Generation","created":"2025-08-21","cited_by_count":52},{"id":"2509.08519","title":"HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning","created":"2025-09-10","cited_by_count":47},{"id":"2108.08420","title":"D3D-HOI: Dynamic 3D Human-Object Interactions from Videos","created":"2021-08-19","cited_by_count":39},{"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":"2511.23002","title":"JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization","created":"2025-11-28","cited_by_count":31},{"id":"2411.17383","title":"AnchorCrafter: Animate Cyber-Anchors Selling Your Products via Human-Object Interacting Video Generation","created":"2024-11-26","cited_by_count":26},{"id":"2506.10568","title":"DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers","created":"2025-06-12","cited_by_count":22},{"id":"2406.07754","title":"HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness","created":"2024-06-11","cited_by_count":21},{"id":"2506.09984","title":"InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions","created":"2025-06-11","cited_by_count":20},{"id":"2511.23475","title":"AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement","created":"2025-11-28","cited_by_count":20},{"id":"2503.13319","title":"MagicDistillation: Weak-to-Strong Video Distillation for Large-Scale Few-Step Synthesis","created":"2025-03-17","cited_by_count":19},{"id":"2503.16942","title":"Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model","created":"2025-03-21","cited_by_count":19},{"id":"2503.05978","title":"MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice","created":"2025-03-07","cited_by_count":16},{"id":"2505.23525","title":"Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization","created":"2025-05-29","cited_by_count":16},{"id":"2405.09985","title":"VirtualModel: Generating Object-ID-retentive Human-object Interaction Image by Diffusion Model for E-commerce Marketing","created":"2024-05-16","cited_by_count":15},{"id":"2410.13370","title":"MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models","created":"2024-10-17","cited_by_count":14},{"id":"2506.08797","title":"HunyuanVideo-HOMA: Generic Human-Object Interaction in Multimodal Driven Human Animation","created":"2025-06-10","cited_by_count":14},{"id":"2506.10915","title":"M4V: Multimodal Mamba for Efficient Text-to-Video Generation","created":"2025-06-12","cited_by_count":12},{"id":"2508.17588","title":"HERO: Hierarchical Extrapolation and Refresh for Efficient World Models","created":"2025-08-25","cited_by_count":9},{"id":"2512.06905","title":"Scaling Zero-Shot Reference-to-Video Generation","created":"2025-12-07","cited_by_count":9},{"id":"2602.12127","title":"PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback","created":"2026-02-12","cited_by_count":9},{"id":"2412.11152","title":"Dual-Schedule Inversion: Training- and Tuning-Free Inversion for Real Image Editing","created":"2024-12-15","cited_by_count":8},{"id":"2510.04577","title":"Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers","created":"2025-10-06","cited_by_count":8},{"id":"2510.22994","title":"SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency","created":"2025-10-27","cited_by_count":7},{"id":"2512.22310","title":"MoFu: Scale-Aware Modulation and Fourier Fusion for Multi-Subject Video Generation","created":"2025-12-26","cited_by_count":6},{"id":"2512.23519","title":"IdentityStory: Taming Your Identity-Preserving Generator for Human-Centric Story Generation","created":"2025-12-29","cited_by_count":6},{"id":"2603.05898","title":"InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generation","created":"2026-03-06","cited_by_count":6},{"id":"2603.02210","title":"HiFi-Inpaint: Towards High-Fidelity Reference-Based Inpainting for Generating Detail-Preserving Human-Product Images","created":"2026-03-02","cited_by_count":5},{"id":"2601.02107","title":"MagicFight: Personalized Martial Arts Combat Video Generation","created":"2026-01-05","cited_by_count":4}],"next_cursor":null}