{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2602.15922","title":"World Action Models are Zero-shot Policies","created":"2026-02-17","cited_by_count":465},{"id":"2501.01423","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models","created":"2025-01-02","cited_by_count":393},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"2303.09556","title":"Efficient Diffusion Training via Min-SNR Weighting Strategy","created":"2023-03-16","cited_by_count":246},{"id":"2504.10483","title":"REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers","created":"2025-04-14","cited_by_count":225},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"2210.06407","title":"Interactive Language: Talking to Robots in Real Time","created":"2022-10-12","cited_by_count":218},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2404.12377","title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","created":"2024-04-18","cited_by_count":195},{"id":"2001.02407","title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","created":"2020-01-08","cited_by_count":190},{"id":"2505.12705","title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","created":"2025-05-19","cited_by_count":179},{"id":"2502.06764","title":"History-Guided Video Diffusion","created":"2025-02-10","cited_by_count":171},{"id":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166},{"id":"2310.08576","title":"Learning to Act from Actionless Videos through Dense Correspondences","created":"2023-10-12","cited_by_count":164},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147},{"id":"2205.14065","title":"Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos","created":"2022-05-27","cited_by_count":139},{"id":"2309.08587","title":"Compositional Foundation Models for Hierarchical Planning","created":"2023-09-15","cited_by_count":95},{"id":"2112.02815","title":"Make It Move: Controllable Image-to-Video Generation with Text Descriptions","created":"2021-12-06","cited_by_count":88},{"id":"2312.04557","title":"GenTron: Diffusion Transformers for Image and Video Generation","created":"2023-12-07","cited_by_count":82},{"id":"2306.04829","title":"Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities","created":"2023-06-07","cited_by_count":78},{"id":"2601.16208","title":"Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders","created":"2026-01-22","cited_by_count":53},{"id":"2310.06907","title":"Self-supervised Object-Centric Learning for Videos","created":"2023-10-10","cited_by_count":49},{"id":"2312.00648","title":"SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers","created":"2023-12-01","cited_by_count":49},{"id":"2211.12824","title":"Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation","created":"2022-11-23","cited_by_count":32},{"id":"2412.14295","title":"Temporally Consistent Object-Centric Learning by Contrasting Slots","created":"2024-12-18","cited_by_count":31},{"id":"2006.11132","title":"Deep Transformation-Invariant Clustering","created":"2020-06-19","cited_by_count":26},{"id":"2410.05203","title":"Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality","created":"2024-10-07","cited_by_count":22},{"id":"2512.17909","title":"Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing","created":"2025-12-19","cited_by_count":22},{"id":"2605.06388","title":"Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models","created":"2026-05-07","cited_by_count":22},{"id":"2205.15821","title":"Unsupervised Image Representation Learning with Deep Latent Particles","created":"2022-05-31","cited_by_count":19},{"id":"2302.11850","title":"Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactions","created":"2023-02-23","cited_by_count":19},{"id":"2503.06170","title":"Object-Centric World Model for Language-Guided Manipulation","created":"2025-03-08","cited_by_count":16},{"id":"2603.04553","title":"Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling","created":"2026-03-04","cited_by_count":15},{"id":"2502.07600","title":"PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning","created":"2025-02-11","cited_by_count":14},{"id":"2110.03473","title":"Unsupervised Image Decomposition with Phase-Correlation Networks","created":"2021-10-07","cited_by_count":6},{"id":"2605.14937","title":"Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations","created":"2026-05-14","cited_by_count":4},{"id":"2502.11655","title":"TextOCVP: Object-Centric Video Prediction with Language Guidance","created":"2025-02-17","cited_by_count":1}],"next_cursor":null}