{"list":"other","total":79,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2309.13101","title":"Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction","created":"2023-09-22","cited_by_count":759},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2205.15285","title":"Fast Dynamic Radiance Fields with Time-Aware Neural Voxels","created":"2022-05-30","cited_by_count":346},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2505.13211","title":"MAGI-1: Autoregressive Video Generation at Scale","created":"2025-05-19","cited_by_count":276},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"2411.02385","title":"How Far is Video Generation from World Model: A Physical Law Perspective","created":"2024-11-04","cited_by_count":212},{"id":"2406.15252","title":"VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation","created":"2024-06-21","cited_by_count":197},{"id":"2410.05363","title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation","created":"2024-10-07","cited_by_count":174},{"id":"2411.14499","title":"Understanding World or Predicting Future? A Comprehensive Survey of World Models","created":"2024-11-21","cited_by_count":166},{"id":"2501.16411","title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding","created":"2025-01-27","cited_by_count":160},{"id":"2106.08261","title":"Physion: Evaluating Physical Prediction from Vision in Humans and Machines","created":"2021-06-15","cited_by_count":153},{"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":"1908.05656","title":"PHYRE: A New Benchmark for Physical Reasoning","created":"2019-08-15","cited_by_count":137},{"id":"2502.20694","title":"WorldModelBench: Judging Video Generation Models As World Models","created":"2025-02-28","cited_by_count":124},{"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":"2503.08153","title":"WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation","created":"2025-03-11","cited_by_count":90},{"id":"2503.17973","title":"PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos","created":"2025-03-23","cited_by_count":87},{"id":"1909.12000","title":"CoPhy: Counterfactual Learning of Physical Dynamics","created":"2019-09-26","cited_by_count":81},{"id":"2406.04338","title":"Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion","created":"2024-06-06","cited_by_count":80},{"id":"2503.23765","title":"STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?","created":"2025-03-31","cited_by_count":79},{"id":"2501.18982","title":"OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation","created":"2025-01-31","cited_by_count":69},{"id":"2205.01089","title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","created":"2022-05-02","cited_by_count":63},{"id":"1804.08018","title":"ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking","created":"2018-04-21","cited_by_count":55},{"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":"2506.09849","title":"IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments","created":"2025-06-11","cited_by_count":52},{"id":"2503.09595","title":"PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop","created":"2025-03-12","cited_by_count":50},{"id":"2406.14927","title":"GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulation","created":"2024-06-21","cited_by_count":49},{"id":"2504.02918","title":"Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems","created":"2025-04-03","cited_by_count":48},{"id":"2412.02617","title":"Improving Dynamic Object Interactions in Text-to-Video Generation with AI Feedback","created":"2024-12-03","cited_by_count":47},{"id":"2012.04293","title":"CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions","created":"2020-12-08","cited_by_count":44},{"id":"2507.12465","title":"PhysX-3D: Physical-Grounded 3D Asset Generation","created":"2025-07-16","cited_by_count":42},{"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":"2505.15929","title":"PhyX: Does Your Model Have the \"Wits\" for Physical Reasoning?","created":"2025-05-21","cited_by_count":38},{"id":"2012.14036","title":"Aerial Imagery Pile burn detection using Deep Learning: the FLAME dataset","created":"2020-12-28","cited_by_count":36},{"id":"2203.01762","title":"NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields","created":"2022-03-03","cited_by_count":36},{"id":"2507.13428","title":"\"PhyWorldBench\": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models","created":"2025-07-17","cited_by_count":36},{"id":"2411.08027","title":"LLMPhy: Parameter-Identifiable Physical Reasoning Combining Large Language Models and Physics Engines","created":"2024-11-12","cited_by_count":30},{"id":"2505.20287","title":"MotionPro: A Precise Motion Controller for Image-to-Video Generation","created":"2025-05-26","cited_by_count":30},{"id":"2311.09048","title":"GRASP: A novel benchmark for evaluating language GRounding And Situated Physics understanding in multimodal language models","created":"2023-11-15","cited_by_count":28},{"id":"2312.06398","title":"NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videos","created":"2023-12-11","cited_by_count":28},{"id":"2305.13291","title":"Materialistic: Selecting Similar Materials in Images","created":"2023-05-22","cited_by_count":26},{"id":"2512.00425","title":"What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards","created":"2025-11-29","cited_by_count":25},{"id":"2505.05469","title":"Generating Physically Stable and Buildable Brick Structures from Text","created":"2025-05-08","cited_by_count":24},{"id":"2508.17437","title":"Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels","created":"2025-08-20","cited_by_count":24},{"id":"2406.00622","title":"Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering","created":"2024-06-02","cited_by_count":18},{"id":"2005.00730","title":"ESPRIT: Explaining Solutions to Physical Reasoning Tasks","created":"2020-05-02","cited_by_count":16},{"id":"2406.04155","title":"Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimization","created":"2024-06-06","cited_by_count":16},{"id":"2503.20822","title":"Synthetic Video Enhances Physical Fidelity in Video Synthesis","created":"2025-03-26","cited_by_count":15},{"id":"2410.01376","title":"Learning Physics From Video: Unsupervised Physical Parameter Estimation for Continuous Dynamical Systems","created":"2024-10-02","cited_by_count":13},{"id":"2506.07865","title":"FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity","created":"2025-06-09","cited_by_count":13},{"id":"2510.22975","title":"VoMP: Predicting Volumetric Mechanical Property Fields","created":"2025-10-27","cited_by_count":13},{"id":"1804.01128","title":"Probing Physics Knowledge Using Tools from Developmental Psychology","created":"2018-04-03","cited_by_count":12},{"id":"2508.09811","title":"TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videos","created":"2025-08-13","cited_by_count":11},{"id":"2412.08619","title":"Physics Context Builders: A Modular Framework for Physical Reasoning in Vision-Language Models","created":"2024-12-11","cited_by_count":10},{"id":"2508.01112","title":"MASIV: Toward Material-Agnostic System Identification from Videos","created":"2025-08-01","cited_by_count":9},{"id":"2109.04683","title":"PIP: Physical Interaction Prediction via Mental Simulation with Span Selection","created":"2021-09-10","cited_by_count":8},{"id":"2406.12769","title":"Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Video","created":"2024-06-18","cited_by_count":8},{"id":"1805.00328","title":"3D-PhysNet: Learning the Intuitive Physics of Non-Rigid Object Deformations","created":"2018-04-25","cited_by_count":7},{"id":"2510.02311","title":"Inferring Dynamic Physical Properties from Video Foundation Models","created":"2025-10-02","cited_by_count":6},{"id":"2504.12684","title":"SOPHY: Learning to Generate Simulation-Ready Objects with Physical Materials","created":"2025-04-17","cited_by_count":5},{"id":"2111.11491","title":"Image Based Reconstruction of Liquids from 2D Surface Detections","created":"2021-11-22","cited_by_count":4},{"id":"1804.05928","title":"Defo-Net: Learning Body Deformation using Generative Adversarial Networks","created":"2018-04-16","cited_by_count":2},{"id":"2311.06284","title":"Efficient Generation of Multimodal Fluid Simulation Data","created":"2023-10-30","cited_by_count":1}],"next_cursor":null}