{"list":"other","total":67,"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":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"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":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340},{"id":"1712.00377","title":"Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering","created":"2017-12-01","cited_by_count":339},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2308.01898","title":"UniSim: A Neural Closed-Loop Sensor Simulator","created":"2023-08-03","cited_by_count":297},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174},{"id":"2410.05363","title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation","created":"2024-10-07","cited_by_count":174},{"id":"2309.02561","title":"Physically Grounded Vision-Language Models for Robotic Manipulation","created":"2023-09-05","cited_by_count":165},{"id":"2501.09038","title":"Do generative video models understand physical principles?","created":"2025-01-14","cited_by_count":161},{"id":"2511.18870","title":"HunyuanVideo 1.5 Technical Report","created":"2025-11-24","cited_by_count":160},{"id":"2604.14148","title":"Seedance 2.0: Advancing Video Generation for World Complexity","created":"2026-04-15","cited_by_count":160},{"id":"2504.00983","title":"WorldScore: A Unified Evaluation Benchmark for World Generation","created":"2025-04-01","cited_by_count":156},{"id":"2503.06800","title":"VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation","created":"2025-03-09","cited_by_count":149},{"id":"2511.00088","title":"Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail","created":"2025-10-30","cited_by_count":146},{"id":"2504.04348","title":"OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning","created":"2025-04-06","cited_by_count":143},{"id":"1908.05656","title":"PHYRE: A New Benchmark for Physical Reasoning","created":"2019-08-15","cited_by_count":137},{"id":"1910.04744","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","created":"2019-10-10","cited_by_count":137},{"id":"2506.05284","title":"Video World Models with Long-term Spatial Memory","created":"2025-06-05","cited_by_count":136},{"id":"2310.01361","title":"GenSim: Generating Robotic Simulation Tasks via Large Language Models","created":"2023-10-02","cited_by_count":125},{"id":"2502.20694","title":"WorldModelBench: Judging Video Generation Models As World Models","created":"2025-02-28","cited_by_count":124},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120},{"id":"2010.04296","title":"CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning","created":"2020-10-08","cited_by_count":109},{"id":"2504.20995","title":"TesserAct: Learning 4D Embodied World Models","created":"2025-04-29","cited_by_count":94},{"id":"2512.13507","title":"Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model","created":"2025-12-15","cited_by_count":80},{"id":"2602.08971","title":"WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models","created":"2026-02-09","cited_by_count":76},{"id":"2406.18522","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","created":"2024-06-26","cited_by_count":75},{"id":"2512.16776","title":"Kling-Omni Technical Report","created":"2025-12-18","cited_by_count":71},{"id":"2306.15668","title":"Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties","created":"2023-06-27","cited_by_count":54},{"id":"2012.04293","title":"CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions","created":"2020-12-08","cited_by_count":44},{"id":"2505.21996","title":"VRAG: Learning World Models for Interactive Video Generation","created":"2025-05-28","cited_by_count":38},{"id":"2506.21215","title":"Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?","created":"2025-06-26","cited_by_count":38},{"id":"2506.09943","title":"CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models","created":"2025-06-11","cited_by_count":35},{"id":"2402.06665","title":"The Essential Role of Causality in Foundation World Models for Embodied AI","created":"2024-02-06","cited_by_count":32},{"id":"2402.06119","title":"ContPhy: Continuum Physical Concept Learning and Reasoning from Videos","created":"2024-02-09","cited_by_count":27},{"id":"2601.01528","title":"DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving","created":"2026-01-04","cited_by_count":21},{"id":"2211.03779","title":"CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","created":"2022-11-07","cited_by_count":13},{"id":"2404.01299","title":"CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes","created":"2024-04-01","cited_by_count":13},{"id":"2506.11034","title":"CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language Models","created":"2025-05-21","cited_by_count":7},{"id":"2503.04556","title":"Compositional Causal Reasoning Evaluation in Language Models","created":"2025-03-06","cited_by_count":6},{"id":"2408.08105","title":"Multimodal Causal Reasoning Benchmark: Challenging Vision Large Language Models to Discern Causal Links Across Modalities","created":"2024-08-15","cited_by_count":5}],"next_cursor":null}