{"list":"other","total":74,"rows":[{"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":"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2008.11200","title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects","created":"2020-08-25","cited_by_count":405},{"id":"2311.01378","title":"Vision-Language Foundation Models as Effective Robot Imitators","created":"2023-11-02","cited_by_count":349},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2104.04631","title":"DexYCB: A Benchmark for Capturing Hand Grasping of Objects","created":"2021-04-09","cited_by_count":325},{"id":"2204.13662","title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation","created":"2022-04-28","cited_by_count":312},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2309.16237","title":"Object Motion Guided Human Motion Synthesis","created":"2023-09-28","cited_by_count":212},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203},{"id":"2308.16905","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","created":"2023-08-31","cited_by_count":182},{"id":"2304.09790","title":"AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation","created":"2023-04-19","cited_by_count":180},{"id":"2311.16097","title":"CG-HOI: Contact-Guided 3D Human-Object Interaction Generation","created":"2023-11-27","cited_by_count":138},{"id":"2403.08629","title":"Scaling Up Dynamic Human-Scene Interaction Modeling","created":"2024-03-13","cited_by_count":137},{"id":"2205.00541","title":"COUCH: Towards Controllable Human-Chair Interactions","created":"2022-05-01","cited_by_count":135},{"id":"2203.15709","title":"OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction","created":"2022-03-29","cited_by_count":131},{"id":"2502.02492","title":"VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models","created":"2025-02-04","cited_by_count":113},{"id":"2312.03913","title":"Controllable Human-Object Interaction Synthesis","created":"2023-12-06","cited_by_count":109},{"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":"2312.02256","title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation","created":"2023-12-04","cited_by_count":89},{"id":"2401.08399","title":"TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding","created":"2024-01-16","cited_by_count":88},{"id":"2503.23377","title":"JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization","created":"2025-03-30","cited_by_count":88},{"id":"2404.00562","title":"Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction","created":"2024-03-31","cited_by_count":86},{"id":"2403.19417","title":"OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion","created":"2024-03-28","cited_by_count":82},{"id":"2307.07511","title":"NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis","created":"2023-07-14","cited_by_count":78},{"id":"2312.04393","title":"PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction","created":"2023-12-07","cited_by_count":76},{"id":"2502.20390","title":"InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions","created":"2025-02-27","cited_by_count":72},{"id":"2411.18179","title":"Prediction with Action: Visual Policy Learning via Joint Denoising Process","created":"2024-11-27","cited_by_count":70},{"id":"2309.16429","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","created":"2023-09-28","cited_by_count":69},{"id":"2403.19652","title":"InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction","created":"2024-03-28","cited_by_count":64},{"id":"2309.07907","title":"Physically Plausible Full-Body Hand-Object Interaction Synthesis","created":"2023-09-14","cited_by_count":52},{"id":"2403.08764","title":"VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis","created":"2024-03-13","cited_by_count":50},{"id":"2407.11385","title":"Omnigrasp: Grasping Diverse Objects with Simulated Humanoids","created":"2024-07-16","cited_by_count":46},{"id":"2406.14558","title":"CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics","created":"2024-06-20","cited_by_count":44},{"id":"2310.02242","title":"Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models","created":"2023-10-03","cited_by_count":43},{"id":"2303.13129","title":"Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations","created":"2023-03-23","cited_by_count":42},{"id":"2309.04509","title":"The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion","created":"2023-09-08","cited_by_count":41},{"id":"2409.08273","title":"Hand-Object Interaction Pretraining from Videos","created":"2024-09-12","cited_by_count":39},{"id":"2402.14810","title":"GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion","created":"2024-02-22","cited_by_count":35},{"id":"2412.04244","title":"GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities","created":"2024-12-05","cited_by_count":33},{"id":"2207.07351","title":"Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space","created":"2022-07-15","cited_by_count":32},{"id":"2403.17422","title":"InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion","created":"2024-03-26","cited_by_count":28},{"id":"2411.17383","title":"AnchorCrafter: Animate Cyber-Anchors Selling Your Products via Human-Object Interacting Video Generation","created":"2024-11-26","cited_by_count":26},{"id":"2409.09300","title":"ManiDext: Hand-Object Manipulation Synthesis via Continuous Correspondence Embeddings and Residual-Guided Diffusion","created":"2024-09-14","cited_by_count":21},{"id":"2412.16212","title":"ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping","created":"2024-12-18","cited_by_count":18},{"id":"2408.02879","title":"Body of Her: A Preliminary Study on End-to-End Humanoid Agent","created":"2024-08-06","cited_by_count":15},{"id":"2310.07206","title":"DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation","created":"2023-10-11","cited_by_count":8},{"id":"2312.10714","title":"Primitive-based 3D Human-Object Interaction Modelling and Programming","created":"2023-12-17","cited_by_count":7}],"next_cursor":null}