{"list":"other","total":59,"rows":[{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"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":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"2405.17398","title":"Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability","created":"2024-05-27","cited_by_count":347},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328},{"id":"2309.09777","title":"DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving","created":"2023-09-18","cited_by_count":261},{"id":"2303.13744","title":"Conditional Image-to-Video Generation with Latent Flow Diffusion Models","created":"2023-03-24","cited_by_count":181},{"id":"2411.14499","title":"Understanding World or Predicting Future? A Comprehensive Survey of World Models","created":"2024-11-21","cited_by_count":166},{"id":"2309.03895","title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","created":"2023-09-07","cited_by_count":164},{"id":"2501.09038","title":"Do generative video models understand physical principles?","created":"2025-01-14","cited_by_count":161},{"id":"2403.14468","title":"AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks","created":"2024-03-21","cited_by_count":154},{"id":"2202.09481","title":"TransDreamer: Reinforcement Learning with Transformer World Models","created":"2022-02-19","cited_by_count":143},{"id":"2501.08331","title":"Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise","created":"2025-01-14","cited_by_count":117},{"id":"2405.04390","title":"DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving","created":"2024-05-07","cited_by_count":93},{"id":"2504.13180","title":"PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding","created":"2025-04-17","cited_by_count":92},{"id":"2310.09615","title":"STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning","created":"2023-10-14","cited_by_count":89},{"id":"2406.09455","title":"Pandora: Towards General World Model with Natural Language Actions and Video States","created":"2024-06-12","cited_by_count":86},{"id":"2510.16732","title":"A Comprehensive Survey on World Models for Embodied AI","created":"2025-10-19","cited_by_count":68},{"id":"2501.11260","title":"A Survey of World Models for Autonomous Driving","created":"2025-01-20","cited_by_count":60},{"id":"2403.05131","title":"Sora as a World Model? A Complete Survey on Text-to-Video Generation","created":"2024-03-08","cited_by_count":53},{"id":"2305.13840","title":"Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback Learning","created":"2023-05-23","cited_by_count":48},{"id":"2305.12328","title":"InstructVid2Vid: Controllable Video Editing with Natural Language Instructions","created":"2023-05-21","cited_by_count":44},{"id":"2509.21309","title":"NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics","created":"2025-09-25","cited_by_count":41},{"id":"2503.14350","title":"VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation","created":"2025-03-18","cited_by_count":40},{"id":"2410.12822","title":"AVID: Adapting Video Diffusion Models to World Models","created":"2024-10-01","cited_by_count":37},{"id":"2506.09943","title":"CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models","created":"2025-06-11","cited_by_count":35},{"id":"2007.06705","title":"Unsupervised object-centric video generation and decomposition in 3D","created":"2020-07-07","cited_by_count":31},{"id":"2307.02064","title":"Facing Off World Model Backbones: RNNs, Transformers, and S4","created":"2023-07-05","cited_by_count":31},{"id":"2506.05046","title":"FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing","created":"2025-06-05","cited_by_count":26},{"id":"2311.15813","title":"FlowZero: Zero-Shot Text-to-Video Synthesis with LLM-Driven Dynamic Scene Syntax","created":"2023-11-27","cited_by_count":19},{"id":"2505.22246","title":"StateSpaceDiffuser: Bringing Long Context to Diffusion World Models","created":"2025-05-28","cited_by_count":19},{"id":"2503.13684","title":"FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models","created":"2025-03-17","cited_by_count":16},{"id":"2503.21056","title":"Online Reasoning Video Segmentation with Just-in-Time Digital Twins","created":"2025-03-27","cited_by_count":11},{"id":"2505.03798","title":"Position: Foundation Models Need Digital Twin Representations","created":"2025-05-01","cited_by_count":10},{"id":"2505.11838","title":"RVTBench: A Benchmark for Visual Reasoning Tasks","created":"2025-05-17","cited_by_count":9},{"id":"2511.14100","title":"Text-Driven Reasoning Video Editing via Reinforcement Learning on Digital Twin Representations","created":"2025-11-18","cited_by_count":3},{"id":"2510.22960","title":"FAME: Fairness-aware Attention-modulated Video Editing","created":"2025-10-27","cited_by_count":2}],"next_cursor":null}