{"list":"other","total":64,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"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":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2209.14687","title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","created":"2022-09-29","cited_by_count":1416},{"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":"2401.08740","title":"SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers","created":"2024-01-16","cited_by_count":737},{"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":"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":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"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":"2303.01418","title":"Human Motion Diffusion as a Generative Prior","created":"2023-03-02","cited_by_count":357},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238},{"id":"2102.04942","title":"Robust Motion In-betweening","created":"2021-02-09","cited_by_count":229},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"2305.12577","title":"Guided Motion Diffusion for Controllable Human Motion Synthesis","created":"2023-05-21","cited_by_count":223},{"id":"2209.00349","title":"FLAME: Free-form Language-based Motion Synthesis & Editing","created":"2022-09-01","cited_by_count":217},{"id":"2211.09707","title":"Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":190},{"id":"2209.04066","title":"TEACH: Temporal Action Composition for 3D Humans","created":"2022-09-09","cited_by_count":176},{"id":"2404.19759","title":"MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model","created":"2024-04-30","cited_by_count":168},{"id":"2312.03596","title":"MMM: Generative Masked Motion Model","created":"2023-12-06","cited_by_count":131},{"id":"2312.15004","title":"FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing","created":"2023-12-22","cited_by_count":106},{"id":"2310.12978","title":"HumanTOMATO: Text-aligned Whole-body Motion Generation","created":"2023-10-19","cited_by_count":104},{"id":"2005.05751","title":"Unpaired Motion Style Transfer from Video to Animation","created":"2020-05-12","cited_by_count":94},{"id":"2405.11126","title":"Flexible Motion In-betweening with Diffusion Models","created":"2024-05-17","cited_by_count":71},{"id":"2211.16016","title":"UDE: A Unified Driving Engine for Human Motion Generation","created":"2022-11-29","cited_by_count":67},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65},{"id":"2202.05274","title":"Motion Puzzle: Arbitrary Motion Style Transfer by Body Part","created":"2022-02-10","cited_by_count":64},{"id":"2304.10417","title":"SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation","created":"2023-04-20","cited_by_count":64},{"id":"2408.00712","title":"MotionFix: Text-Driven 3D Human Motion Editing","created":"2024-08-01","cited_by_count":64},{"id":"2311.16468","title":"AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond","created":"2023-11-28","cited_by_count":63},{"id":"2410.21747","title":"MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding","created":"2024-10-29","cited_by_count":59},{"id":"2312.11538","title":"Iterative Motion Editing with Natural Language","created":"2023-12-15","cited_by_count":40},{"id":"2405.16273","title":"M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation","created":"2024-05-25","cited_by_count":38},{"id":"2407.12783","title":"SMooDi: Stylized Motion Diffusion Model","created":"2024-07-17","cited_by_count":37},{"id":"2401.13505","title":"Generative Human Motion Stylization in Latent Space","created":"2024-01-24","cited_by_count":30},{"id":"2404.01700","title":"MotionChain: Conversational Motion Controllers via Multimodal Prompts","created":"2024-04-02","cited_by_count":30},{"id":"2409.15904","title":"Unimotion: Unifying 3D Human Motion Synthesis and Understanding","created":"2024-09-24","cited_by_count":30},{"id":"2407.08394","title":"Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers","created":"2024-07-11","cited_by_count":24},{"id":"2410.04534","title":"UniMuMo: Unified Text, Music and Motion Generation","created":"2024-10-06","cited_by_count":19},{"id":"2405.03485","title":"LGTM: Local-to-Global Text-Driven Human Motion Diffusion Model","created":"2024-05-06","cited_by_count":18},{"id":"2409.00587","title":"FLUX that Plays Music","created":"2024-09-01","cited_by_count":18},{"id":"2311.16471","title":"A Unified Framework for Multimodal, Multi-Part Human Motion Synthesis","created":"2023-11-28","cited_by_count":12},{"id":"2407.15408","title":"Chronologically Accurate Retrieval for Temporal Grounding of Motion-Language Models","created":"2024-07-22","cited_by_count":12},{"id":"2407.11532","title":"Length-Aware Motion Synthesis via Latent Diffusion","created":"2024-07-16","cited_by_count":10},{"id":"2409.18128","title":"FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner","created":"2024-09-26","cited_by_count":6}],"next_cursor":null}