{"list":"other","total":84,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"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":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"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":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"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":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"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":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2506.15564","title":"Show-o2: Improved Native Unified Multimodal Models","created":"2025-06-18","cited_by_count":250},{"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":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"2409.06662","title":"World-Grounded Human Motion Recovery via Gravity-View Coordinates","created":"2024-09-10","cited_by_count":137},{"id":"2510.26583","title":"Emu3.5: Native Multimodal Models are World Learners","created":"2025-10-30","cited_by_count":132},{"id":"2412.15188","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","created":"2024-12-19","cited_by_count":120},{"id":"2309.00796","title":"AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism","created":"2023-09-02","cited_by_count":117},{"id":"2505.05472","title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","created":"2025-05-08","cited_by_count":109},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98},{"id":"2212.03741","title":"FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation","created":"2022-12-07","cited_by_count":88},{"id":"2303.15380","title":"Hi4D: 4D Instance Segmentation of Close Human Interaction","created":"2023-03-27","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":"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":"2401.10208","title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer","created":"2024-01-18","cited_by_count":80},{"id":"2201.04439","title":"Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases","created":"2022-01-12","cited_by_count":72},{"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":"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":"2508.10711","title":"NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale","created":"2025-08-14","cited_by_count":57},{"id":"2412.14559","title":"ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model","created":"2024-12-19","cited_by_count":53},{"id":"2412.08635","title":"Multimodal Latent Language Modeling with Next-Token Diffusion","created":"2024-12-11","cited_by_count":48},{"id":"2405.17013","title":"Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs","created":"2024-05-27","cited_by_count":47},{"id":"2507.09122","title":"SnapMoGen: Human Motion Generation from Expressive Texts","created":"2025-07-12","cited_by_count":47},{"id":"2409.16280","title":"MonoFormer: One Transformer for Both Diffusion and Autoregression","created":"2024-09-24","cited_by_count":46},{"id":"2012.10366","title":"Learning Complex 3D Human Self-Contact","created":"2020-12-18","cited_by_count":40},{"id":"2507.06119","title":"Omni-Video: Democratizing Unified Video Understanding and Generation","created":"2025-07-08","cited_by_count":40},{"id":"2506.24086","title":"MotionGPT3: Human Motion as a Second Modality","created":"2025-06-30","cited_by_count":37},{"id":"2404.01700","title":"MotionChain: Conversational Motion Controllers via Multimodal Prompts","created":"2024-04-02","cited_by_count":30},{"id":"2305.08953","title":"Motion Question Answering via Modular Motion Programs","created":"2023-05-15","cited_by_count":27},{"id":"2411.19527","title":"DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding","created":"2024-11-29","cited_by_count":19},{"id":"2510.16258","title":"Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset","created":"2025-10-17","cited_by_count":19},{"id":"2412.00174","title":"SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters","created":"2024-11-29","cited_by_count":18},{"id":"2509.21574","title":"X-Streamer: Unified Human World Modeling with Audiovisual Interaction","created":"2025-09-25","cited_by_count":18},{"id":"2509.24335","title":"Hyperspherical Latents Improve Continuous-Token Autoregressive Generation","created":"2025-09-29","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":"2411.18447","title":"Continuous Autoregressive Models with Noise Augmentation Avoid Error Accumulation","created":"2024-11-27","cited_by_count":12},{"id":"2507.11949","title":"MOSPA: Human Motion Generation Driven by Spatial Audio","created":"2025-07-16","cited_by_count":12},{"id":"2510.27688","title":"Continuous Autoregressive Language Models","created":"2025-10-31","cited_by_count":10},{"id":"2404.14745","title":"You Think, You ACT: The New Task of Arbitrary Text to Motion Generation","created":"2024-04-23","cited_by_count":8},{"id":"2510.04637","title":"Social Agent: Mastering Dyadic Nonverbal Behavior Generation via Conversational LLM Agents","created":"2025-10-06","cited_by_count":8},{"id":"2512.22808","title":"EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation","created":"2025-12-28","cited_by_count":7},{"id":"2508.01984","title":"IMoRe: Implicit Program-Guided Reasoning for Human Motion Q&A","created":"2025-08-04","cited_by_count":5},{"id":"2510.17937","title":"UniRL-Zero: Reinforcement Learning on Unified Models with Joint Language Model and Diffusion Model Experts","created":"2025-10-20","cited_by_count":5},{"id":"2505.20920","title":"HuMoCon: Concept Discovery for Human Motion Understanding","created":"2025-05-27","cited_by_count":4},{"id":"2511.01463","title":"HMVLM: Human Motion-Vision-Lanuage Model via MoE LoRA","created":"2025-11-03","cited_by_count":4},{"id":"2503.07323","title":"Navigating Motion Agents in Dynamic and Cluttered Environments through LLM Reasoning","created":"2025-03-10","cited_by_count":2}],"next_cursor":null}