{"list":"other","total":80,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"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":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"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":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2306.05284","title":"Simple and Controllable Music Generation","created":"2023-06-08","cited_by_count":488},{"id":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"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":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"id":"2203.13055","title":"Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory","created":"2022-03-24","cited_by_count":212},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163},{"id":"2411.07975","title":"JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation","created":"2024-11-12","cited_by_count":163},{"id":"2306.10900","title":"MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators","created":"2023-06-19","cited_by_count":145},{"id":"2312.03913","title":"Controllable Human-Object Interaction Synthesis","created":"2023-12-06","cited_by_count":109},{"id":"2405.20340","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","created":"2024-05-30","cited_by_count":90},{"id":"2405.11126","title":"Flexible Motion In-betweening with Diffusion Models","created":"2024-05-17","cited_by_count":71},{"id":"2404.01284","title":"Large Motion Model for Unified Multi-Modal Motion Generation","created":"2024-04-01","cited_by_count":65},{"id":"2408.00712","title":"MotionFix: Text-Driven 3D Human Motion Editing","created":"2024-08-01","cited_by_count":64},{"id":"2410.07093","title":"LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning","created":"2024-10-09","cited_by_count":59},{"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":"2203.15536","title":"BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information","created":"2022-03-29","cited_by_count":51},{"id":"2503.19901","title":"TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization","created":"2025-03-25","cited_by_count":51},{"id":"2503.06955","title":"Motion Anything: Any to Motion Generation","created":"2025-03-10","cited_by_count":42},{"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":"2309.01372","title":"DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion","created":"2023-09-04","cited_by_count":37},{"id":"2504.02478","title":"MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities","created":"2025-04-03","cited_by_count":30},{"id":"2503.16430","title":"Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation","created":"2025-03-20","cited_by_count":29},{"id":"2411.19527","title":"DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding","created":"2024-11-29","cited_by_count":19},{"id":"2403.00691","title":"Tri-Modal Motion Retrieval by Learning a Joint Embedding Space","created":"2024-03-01","cited_by_count":16},{"id":"2411.19786","title":"MoTe: Learning Motion-Text Diffusion Model for Multiple Generation Tasks","created":"2024-11-29","cited_by_count":13},{"id":"2410.05628","title":"A Unified Framework for Motion Reasoning and Generation in Human Interaction","created":"2024-10-08","cited_by_count":5},{"id":"2411.01805","title":"MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence","created":"2024-11-04","cited_by_count":5}],"next_cursor":null}