{"list":"other","total":82,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"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":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"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":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","cited_by_count":368},{"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":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"1607.03827","title":"The KIT Motion-Language Dataset","created":"2016-07-13","cited_by_count":338},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"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":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198},{"id":"1906.04160","title":"Learning Individual Styles of Conversational Gesture","created":"2019-06-10","cited_by_count":191},{"id":"2211.09707","title":"Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models","created":"2022-11-17","cited_by_count":190},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178},{"id":"2502.20321","title":"UniTok: A Unified Tokenizer for Visual Generation and Understanding","created":"2025-02-27","cited_by_count":153},{"id":"2312.03596","title":"MMM: Generative Masked Motion Model","created":"2023-12-06","cited_by_count":131},{"id":"2303.09119","title":"Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation","created":"2023-03-16","cited_by_count":129},{"id":"2309.00796","title":"AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism","created":"2023-09-02","cited_by_count":117},{"id":"1710.05298","title":"Text2Action: Generative Adversarial Synthesis from Language to Action","created":"2017-10-15","cited_by_count":106},{"id":"2307.10894","title":"Human Motion Generation: A Survey","created":"2023-07-20","cited_by_count":96},{"id":"2410.01756","title":"ImageFolder: Autoregressive Image Generation with Folded Tokens","created":"2024-10-02","cited_by_count":94},{"id":"2312.02256","title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation","created":"2023-12-04","cited_by_count":89},{"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":"2308.14480","title":"Priority-Centric Human Motion Generation in Discrete Latent Space","created":"2023-08-28","cited_by_count":67},{"id":"2410.07093","title":"LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning","created":"2024-10-09","cited_by_count":59},{"id":"2305.09662","title":"Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation","created":"2023-05-16","cited_by_count":56},{"id":"2412.10958","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer","created":"2024-12-14","cited_by_count":56},{"id":"2403.19435","title":"BAMM: Bidirectional Autoregressive Motion Model","created":"2024-03-28","cited_by_count":55},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","cited_by_count":53},{"id":"2405.05691","title":"StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework","created":"2024-05-09","cited_by_count":50},{"id":"2507.09122","title":"SnapMoGen: Human Motion Generation from Expressive Texts","created":"2025-07-12","cited_by_count":47},{"id":"2503.06955","title":"Motion Anything: Any to Motion Generation","created":"2025-03-10","cited_by_count":42},{"id":"2409.17686","title":"MoGenTS: Motion Generation based on Spatial-Temporal Joint Modeling","created":"2024-09-26","cited_by_count":41},{"id":"2303.12337","title":"Music-Driven Group Choreography","created":"2023-03-22","cited_by_count":37},{"id":"2309.01372","title":"DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion","created":"2023-09-04","cited_by_count":37},{"id":"2412.05796","title":"Language-Guided Image Tokenization for Generation","created":"2024-12-08","cited_by_count":36},{"id":"2506.05289","title":"Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model","created":"2025-06-05","cited_by_count":20},{"id":"2411.19527","title":"DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding","created":"2024-11-29","cited_by_count":19},{"id":"2308.09611","title":"Language-guided Human Motion Synthesis with Atomic Actions","created":"2023-08-18","cited_by_count":17},{"id":"2312.04036","title":"DiffusionPhase: Motion Diffusion in Frequency Domain","created":"2023-12-07","cited_by_count":16},{"id":"2411.06481","title":"KMM: Key Frame Mask Mamba for Extended Motion Generation","created":"2024-11-10","cited_by_count":16},{"id":"2305.04195","title":"Cross-Modal Retrieval for Motion and Text via DropTriple Loss","created":"2023-05-07","cited_by_count":11},{"id":"2503.08354","title":"Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis","created":"2025-03-11","cited_by_count":10},{"id":"2410.14508","title":"LEAD: Latent Realignment for Human Motion Diffusion","created":"2024-10-18","cited_by_count":9},{"id":"2503.14919","title":"GenM$^3$: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation","created":"2025-03-19","cited_by_count":6},{"id":"2511.01200","title":"MoSa: Motion Generation with Scalable Autoregressive Modeling","created":"2025-11-03","cited_by_count":5},{"id":"2508.08991","title":"Spatial-Temporal Multi-Scale Quantization for Flexible Motion Generation","created":"2025-08-12","cited_by_count":3}],"next_cursor":null}