{"list":"other","total":83,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2002.09797","title":"Reliable Fidelity and Diversity Metrics for Generative Models","created":"2020-02-23","cited_by_count":434},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"2406.02507","title":"Guiding a Diffusion Model with a Bad Version of Itself","created":"2024-06-04","cited_by_count":299},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"id":"2212.09478","title":"MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation","created":"2022-12-19","cited_by_count":227},{"id":"2209.00349","title":"FLAME: Free-form Language-based Motion Synthesis & Editing","created":"2022-09-01","cited_by_count":217},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"2211.08332","title":"Versatile Diffusion: Text, Images and Variations All in One Diffusion Model","created":"2022-11-15","cited_by_count":199},{"id":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198},{"id":"2303.06555","title":"One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale","created":"2023-03-12","cited_by_count":187},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2404.19759","title":"MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model","created":"2024-04-30","cited_by_count":168},{"id":"2406.02509","title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","created":"2024-06-04","cited_by_count":166},{"id":"2503.09642","title":"Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k","created":"2025-03-12","cited_by_count":163},{"id":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156},{"id":"2302.12827","title":"Decoupling Human and Camera Motion from Videos in the Wild","created":"2023-02-24","cited_by_count":142},{"id":"2312.03596","title":"MMM: Generative Masked Motion Model","created":"2023-12-06","cited_by_count":131},{"id":"2410.15957","title":"CamI2V: Camera-Controlled Image-to-Video Diffusion Model","created":"2024-10-21","cited_by_count":120},{"id":"2402.17723","title":"Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners","created":"2024-02-27","cited_by_count":111},{"id":"2403.17346","title":"TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos","created":"2024-03-26","cited_by_count":106},{"id":"2005.04208","title":"Condensed Movies: Story Based Retrieval with Contextual Embeddings","created":"2020-05-08","cited_by_count":95},{"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":"2306.02850","title":"TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environments","created":"2023-06-05","cited_by_count":91},{"id":"2401.08559","title":"Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation","created":"2024-01-16","cited_by_count":91},{"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":"2411.16575","title":"Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression","created":"2024-11-25","cited_by_count":85},{"id":"2403.18036","title":"Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance","created":"2024-03-26","cited_by_count":80},{"id":"2501.00289","title":"Dual Diffusion for Unified Image Generation and Understanding","created":"2024-12-31","cited_by_count":76},{"id":"2411.08128","title":"CameraHMR: Aligning People with Perspective","created":"2024-11-12","cited_by_count":65},{"id":"2504.15376","title":"Towards Understanding Camera Motions in Any Video","created":"2025-04-21","cited_by_count":64},{"id":"2410.03187","title":"Autonomous Character-Scene Interaction Synthesis from Text Instruction","created":"2024-10-04","cited_by_count":56},{"id":"2411.02319","title":"GenXD: Generating Any 3D and 4D Scenes","created":"2024-11-04","cited_by_count":50},{"id":"2405.07784","title":"Generating Human Motion in 3D Scenes from Text Descriptions","created":"2024-05-13","cited_by_count":49},{"id":"2503.20853","title":"Unified Multimodal Discrete Diffusion","created":"2025-03-26","cited_by_count":49},{"id":"2504.16064","title":"Boosting Generative Image Modeling via Joint Image-Feature Synthesis","created":"2025-04-22","cited_by_count":45},{"id":"2405.15763","title":"FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis","created":"2024-05-24","cited_by_count":42},{"id":"2211.14842","title":"Unified Discrete Diffusion for Simultaneous Vision-Language Generation","created":"2022-11-27","cited_by_count":39},{"id":"2310.13768","title":"PACE: Human and Camera Motion Estimation from in-the-wild Videos","created":"2023-10-20","cited_by_count":34},{"id":"2501.05098","title":"Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset","created":"2025-01-09","cited_by_count":33},{"id":"2405.18483","title":"Towards Open Domain Text-Driven Synthesis of Multi-Person Motions","created":"2024-05-28","cited_by_count":29},{"id":"2504.17788","title":"Dynamic Camera Poses and Where to Find Them","created":"2025-04-24","cited_by_count":27},{"id":"2407.01516","title":"E.T. the Exceptional Trajectories: Text-to-camera-trajectory generation with character awareness","created":"2024-07-01","cited_by_count":25},{"id":"2405.17842","title":"MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation","created":"2024-05-28","cited_by_count":23},{"id":"2410.10802","title":"Boosting Camera Motion Control for Video Diffusion Transformers","created":"2024-10-14","cited_by_count":20},{"id":"2402.16143","title":"Cinematographic Camera Diffusion Model","created":"2024-02-25","cited_by_count":18},{"id":"2412.14158","title":"AKiRa: Augmentation Kit on Rays for optical video generation","created":"2024-12-18","cited_by_count":18},{"id":"2504.07083","title":"GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography","created":"2025-04-09","cited_by_count":18},{"id":"1910.06988","title":"Autonomous Aerial Cinematography In Unstructured Environments With Learned Artistic Decision-Making","created":"2019-10-15","cited_by_count":16},{"id":"2303.15427","title":"JAWS: Just A Wild Shot for Cinematic Transfer in Neural Radiance Fields","created":"2023-03-27","cited_by_count":13},{"id":"2311.17754","title":"Cinematic Behavior Transfer via NeRF-based Differentiable Filming","created":"2023-11-29","cited_by_count":12},{"id":"2503.16801","title":"Auto-Regressive Diffusion for Generating 3D Human-Object Interactions","created":"2025-03-21","cited_by_count":12},{"id":"2408.12601","title":"DreamCinema: Cinematic Transfer with Free Camera and 3D Character","created":"2024-08-22","cited_by_count":9},{"id":"2410.14508","title":"LEAD: Latent Realignment for Human Motion Diffusion","created":"2024-10-18","cited_by_count":9},{"id":"2403.13667","title":"DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance","created":"2024-03-20","cited_by_count":8},{"id":"2412.00112","title":"BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis","created":"2024-11-28","cited_by_count":6},{"id":"2409.14925","title":"DanceCamAnimator: Keyframe-Based Controllable 3D Dance Camera Synthesis","created":"2024-09-23","cited_by_count":3}],"next_cursor":null}