{"list":"other","total":80,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"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":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"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":"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":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"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":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2312.17090","title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","created":"2023-12-28","cited_by_count":503},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425},{"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":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250},{"id":"2509.20427","title":"Seedream 4.0: Toward Next-generation Multimodal Image Generation","created":"2025-09-24","cited_by_count":249},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2407.08136","title":"EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions","created":"2024-07-11","cited_by_count":196},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175},{"id":"2405.04233","title":"Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models","created":"2024-05-07","cited_by_count":160},{"id":"2303.05125","title":"Cones: Concept Neurons in Diffusion Models for Customized Generation","created":"2023-03-09","cited_by_count":150},{"id":"2409.06662","title":"World-Grounded Human Motion Recovery via Gravity-View Coordinates","created":"2024-09-10","cited_by_count":137},{"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":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87},{"id":"2510.08377","title":"UniVideo: Unified Understanding, Generation, and Editing for Videos","created":"2025-10-09","cited_by_count":87},{"id":"2503.15451","title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space","created":"2025-03-19","cited_by_count":86},{"id":"2506.18866","title":"OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation","created":"2025-06-23","cited_by_count":83},{"id":"2504.04842","title":"FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis","created":"2025-04-07","cited_by_count":77},{"id":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69},{"id":"2507.07095","title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","created":"2025-07-09","cited_by_count":68},{"id":"2501.06187","title":"Multi-subject Open-set Personalization in Video Generation","created":"2025-01-10","cited_by_count":66},{"id":"2505.22647","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","created":"2025-05-28","cited_by_count":66},{"id":"2502.06145","title":"Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance","created":"2025-02-10","cited_by_count":61},{"id":"2503.10625","title":"LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds","created":"2025-03-13","cited_by_count":61},{"id":"2404.15789","title":"MotionMaster: Training-free Camera Motion Transfer For Video Generation","created":"2024-04-24","cited_by_count":51},{"id":"2312.08963","title":"LEMON: Learning 3D Human-Object Interaction Relation from 2D Images","created":"2023-12-14","cited_by_count":49},{"id":"2503.10076","title":"VMBench: A Benchmark for Perception-Aligned Video Motion Generation","created":"2025-03-13","cited_by_count":49},{"id":"2503.19907","title":"FullDiT: Multi-Task Video Generative Foundation Model with Full Attention","created":"2025-03-25","cited_by_count":47},{"id":"2509.08519","title":"HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning","created":"2025-09-10","cited_by_count":47},{"id":"2312.02928","title":"LivePhoto: Real Image Animation with Text-guided Motion Control","created":"2023-12-05","cited_by_count":44},{"id":"2405.15763","title":"FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis","created":"2024-05-24","cited_by_count":42},{"id":"2412.09645","title":"Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models","created":"2024-12-10","cited_by_count":41},{"id":"2508.14033","title":"InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing","created":"2025-08-19","cited_by_count":41},{"id":"2409.01876","title":"CyberHost: Taming Audio-driven Avatar Diffusion Model with Region Codebook Attention","created":"2024-09-03","cited_by_count":39},{"id":"2412.09349","title":"DisPose: Disentangling Pose Guidance for Controllable Human Image Animation","created":"2024-12-12","cited_by_count":35},{"id":"2512.02014","title":"TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models","created":"2025-12-01","cited_by_count":34},{"id":"2508.19209","title":"OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation","created":"2025-08-26","cited_by_count":32},{"id":"2410.05227","title":"The Dawn of Video Generation: Preliminary Explorations with SORA-like Models","created":"2024-10-07","cited_by_count":31},{"id":"2503.23307","title":"MoCha: Towards Movie-Grade Talking Character Synthesis","created":"2025-03-30","cited_by_count":31},{"id":"2507.03905","title":"EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation","created":"2025-07-05","cited_by_count":29},{"id":"2411.19626","title":"GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding","created":"2024-11-29","cited_by_count":28},{"id":"2408.17135","title":"TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation","created":"2024-08-30","cited_by_count":27},{"id":"2405.13659","title":"EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views","created":"2024-05-22","cited_by_count":26},{"id":"2503.23452","title":"VideoGen-Eval: Agent-based System for Video Generation Evaluation","created":"2025-03-30","cited_by_count":23},{"id":"2509.09595","title":"Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis","created":"2025-09-11","cited_by_count":21},{"id":"2409.07649","title":"DiffTED: One-shot Audio-driven TED Talk Video Generation with Diffusion-based Co-speech Gestures","created":"2024-09-11","cited_by_count":20},{"id":"2506.01801","title":"OmniV2V: Versatile Video Generation and Editing via Dynamic Content Manipulation","created":"2025-06-02","cited_by_count":19},{"id":"2501.08332","title":"MangaNinja: Line Art Colorization with Precise Reference Following","created":"2025-01-14","cited_by_count":17},{"id":"2506.07848","title":"PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement","created":"2025-06-09","cited_by_count":16},{"id":"2508.15720","title":"WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception","created":"2025-08-21","cited_by_count":16},{"id":"2503.08270","title":"HERO: Human Reaction Generation from Videos","created":"2025-03-11","cited_by_count":15},{"id":"2510.11026","title":"GIR-Bench: Versatile Benchmark for Generating Images with Reasoning","created":"2025-10-13","cited_by_count":15},{"id":"2506.00830","title":"SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers","created":"2025-06-01","cited_by_count":14},{"id":"2505.18078","title":"DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation","created":"2025-05-23","cited_by_count":13},{"id":"2504.06982","title":"SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets","created":"2025-04-09","cited_by_count":12},{"id":"2409.19650","title":"Grounding 3D Scene Affordance From Egocentric Interactions","created":"2024-09-29","cited_by_count":11},{"id":"2411.04079","title":"Textual Decomposition Then Sub-motion-space Scattering for Open-Vocabulary Motion Generation","created":"2024-11-06","cited_by_count":8},{"id":"2510.14874","title":"TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions","created":"2025-10-16","cited_by_count":8},{"id":"2512.13465","title":"PoseAnything: Universal Pose-guided Video Generation with Part-aware Temporal Coherence","created":"2025-12-15","cited_by_count":5},{"id":"2511.23146","title":"InstanceV: Instance-Level Video Generation","created":"2025-11-28","cited_by_count":3}],"next_cursor":null}