{"list":"other","total":61,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"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":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2403.14624","title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","created":"2024-03-21","cited_by_count":586},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"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":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2312.00063","title":"MoMask: Generative Masked Modeling of 3D Human Motions","created":"2023-11-29","cited_by_count":400},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","cited_by_count":368},{"id":"2207.09519","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","created":"2022-07-19","cited_by_count":362},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239},{"id":"2310.08580","title":"OmniControl: Control Any Joint at Any Time for Human Motion Generation","created":"2023-10-12","cited_by_count":238},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194},{"id":"2211.11682","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","created":"2022-11-21","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":"2312.16217","title":"ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation","created":"2023-12-24","cited_by_count":162},{"id":"1701.01036","title":"Demystifying Neural Style Transfer","created":"2017-01-04","cited_by_count":152},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142},{"id":"2304.01893","title":"Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion","created":"2023-04-04","cited_by_count":138},{"id":"2312.03596","title":"MMM: Generative Masked Motion Model","created":"2023-12-06","cited_by_count":131},{"id":"2501.13926","title":"Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step","created":"2025-01-23","cited_by_count":131},{"id":"2502.09621","title":"MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency","created":"2025-02-13","cited_by_count":125},{"id":"2407.08739","title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine","created":"2024-07-11","cited_by_count":113},{"id":"2209.14169","title":"CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention","created":"2022-09-28","cited_by_count":103},{"id":"2312.14074","title":"LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding","created":"2023-12-21","cited_by_count":95},{"id":"2005.05751","title":"Unpaired Motion Style Transfer from Video to Animation","created":"2020-05-12","cited_by_count":94},{"id":"2311.17135","title":"TLControl: Trajectory and Language Control for Human Motion Synthesis","created":"2023-11-28","cited_by_count":94},{"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":"2401.08559","title":"Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation","created":"2024-01-16","cited_by_count":91},{"id":"2405.20340","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","created":"2024-05-30","cited_by_count":90},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","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":"2302.05905","title":"Single Motion Diffusion","created":"2023-02-12","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":"2403.19652","title":"InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction","created":"2024-03-28","cited_by_count":64},{"id":"2403.17827","title":"DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions","created":"2024-03-26","cited_by_count":62},{"id":"2410.07093","title":"LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning","created":"2024-10-09","cited_by_count":59},{"id":"2403.19435","title":"BAMM: Bidirectional Autoregressive Motion Model","created":"2024-03-28","cited_by_count":55},{"id":"2405.07784","title":"Generating Human Motion in 3D Scenes from Text Descriptions","created":"2024-05-13","cited_by_count":49},{"id":"2403.11208","title":"THOR: Text to Human-Object Interaction Diffusion via Relation Intervention","created":"2024-03-17","cited_by_count":46},{"id":"2406.06508","title":"Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer","created":"2024-06-10","cited_by_count":31},{"id":"2401.13505","title":"Generative Human Motion Stylization in Latent Space","created":"2024-01-24","cited_by_count":30},{"id":"2008.10162","title":"Hierarchical Style-based Networks for Motion Synthesis","created":"2020-08-24","cited_by_count":23},{"id":"2503.10627","title":"SciVerse: Unveiling the Knowledge Comprehension and Visual Reasoning of LMMs on Multi-modal Scientific Problems","created":"2025-03-13","cited_by_count":22},{"id":"2402.16664","title":"LLM-Assisted Multi-Teacher Continual Learning for Visual Question Answering in Robotic Surgery","created":"2024-02-26","cited_by_count":20},{"id":"2306.11970","title":"RSMT: Real-time Stylized Motion Transition for Characters","created":"2023-06-21","cited_by_count":19},{"id":"2403.06225","title":"MoST: Motion Style Transformer between Diverse Action Contents","created":"2024-03-10","cited_by_count":18},{"id":"2502.09620","title":"Exploring the Potential of Encoder-free Architectures in 3D LMMs","created":"2025-02-13","cited_by_count":16},{"id":"2410.14508","title":"LEAD: Latent Realignment for Human Motion Diffusion","created":"2024-10-18","cited_by_count":9},{"id":"2503.10529","title":"PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models","created":"2025-03-13","cited_by_count":8}],"next_cursor":null}