{"list":"other","total":84,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2505.06111","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","created":"2025-05-09","cited_by_count":410},{"id":"2503.06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","created":"2025-03-09","cited_by_count":405},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341},{"id":"2410.11758","title":"Latent Action Pretraining from Videos","created":"2024-10-15","cited_by_count":321},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2512.13030","title":"Motus: A Unified Latent Action World Model","created":"2025-12-15","cited_by_count":251},{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174},{"id":"2106.08261","title":"Physion: Evaluating Physical Prediction from Vision in Humans and Machines","created":"2021-06-15","cited_by_count":153},{"id":"2405.15223","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","created":"2024-05-24","cited_by_count":146},{"id":"2312.10812","title":"Learning to Act without Actions","created":"2023-12-17","cited_by_count":121},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116},{"id":"2503.18938","title":"AdaWorld: Learning Adaptable World Models with Latent Actions","created":"2025-03-24","cited_by_count":114},{"id":"2402.03161","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","created":"2024-02-05","cited_by_count":100},{"id":"2505.23656","title":"VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models","created":"2025-05-29","cited_by_count":98},{"id":"2503.08153","title":"WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation","created":"2025-03-11","cited_by_count":90},{"id":"2412.04445","title":"Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos","created":"2024-12-05","cited_by_count":69},{"id":"2505.03729","title":"Visual Imitation Enables Contextual Humanoid Control","created":"2025-05-06","cited_by_count":68},{"id":"2506.15675","title":"Sekai: A Video Dataset towards World Exploration","created":"2025-06-18","cited_by_count":67},{"id":"2205.01089","title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","created":"2022-05-02","cited_by_count":63},{"id":"2506.13691","title":"UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions","created":"2025-06-16","cited_by_count":57},{"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":"2503.23368","title":"VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior","created":"2025-03-30","cited_by_count":52},{"id":"2506.09849","title":"IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments","created":"2025-06-11","cited_by_count":52},{"id":"2405.13557","title":"MotionCraft: Physics-based Zero-Shot Video Generation","created":"2024-05-22","cited_by_count":48},{"id":"2601.05230","title":"Learning Latent Action World Models In The Wild","created":"2026-01-08","cited_by_count":47},{"id":"2305.18499","title":"Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning","created":"2023-05-29","cited_by_count":45},{"id":"2501.09781","title":"VideoWorld: Exploring Knowledge Learning from Unlabeled Videos","created":"2025-01-16","cited_by_count":43},{"id":"2403.14148","title":"Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition","created":"2024-03-21","cited_by_count":42},{"id":"2511.09057","title":"PAN: A World Model for General, Actionable, and Long-Horizon World Simulation","created":"2025-11-12","cited_by_count":36},{"id":"2603.24458","title":"OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning","created":"2026-03-25","cited_by_count":27},{"id":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","cited_by_count":26},{"id":"2510.11512","title":"LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference","created":"2025-10-13","cited_by_count":16},{"id":"2510.19022","title":"MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models","created":"2025-10-21","cited_by_count":16},{"id":"2411.13552","title":"REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents","created":"2024-11-20","cited_by_count":14},{"id":"2412.17726","title":"VidTwin: Video VAE with Decoupled Structure and Dynamics","created":"2024-12-23","cited_by_count":14},{"id":"2603.06408","title":"Physical Simulator In-the-Loop Video Generation","created":"2026-03-06","cited_by_count":14},{"id":"2510.26433","title":"Co-Evolving Latent Action World Models","created":"2025-10-30","cited_by_count":13},{"id":"2303.03684","title":"MOSO: Decomposing MOtion, Scene and Object for Video Prediction","created":"2023-03-07","cited_by_count":12},{"id":"2602.10102","title":"VideoWorld 2: Learning Transferable Knowledge from Real-world Videos","created":"2026-02-10","cited_by_count":12},{"id":"2605.10806","title":"PhyGround: Benchmarking Physical Reasoning in Generative World Models","created":"2026-05-11","cited_by_count":12},{"id":"2603.11041","title":"DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving","created":"2026-03-11","cited_by_count":11},{"id":"2511.23428","title":"DisMo: Disentangled Motion Representations for Open-World Motion Transfer","created":"2025-11-28","cited_by_count":10},{"id":"2602.10104","title":"Olaf-World: Orienting Latent Actions for Video World Modeling","created":"2026-02-10","cited_by_count":10},{"id":"2604.19734","title":"UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling","created":"2026-04-21","cited_by_count":10},{"id":"2605.15725","title":"DiLA: Disentangled Latent Action World Models","created":"2026-05-15","cited_by_count":10},{"id":"2412.04432","title":"Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation","created":"2024-12-05","cited_by_count":9},{"id":"2503.03708","title":"Rethinking Video Tokenization: A Conditioned Diffusion-based Approach","created":"2025-03-05","cited_by_count":9},{"id":"2506.07136","title":"MotionStrata: Hierarchical Motion Latents for Compact Video Autoencoding","created":"2025-06-08","cited_by_count":9},{"id":"2606.18943","title":"Physics-IQ Verified","created":"2026-06-17","cited_by_count":9},{"id":"2602.16229","title":"Factored Latent Action World Models","created":"2026-02-18","cited_by_count":7},{"id":"2604.12887","title":"VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization","created":"2026-04-14","cited_by_count":6},{"id":"2412.04446","title":"DiCoDe: Diffusion-Compressed Deep Tokens for Autoregressive Video Generation with Language Models","created":"2024-12-05","cited_by_count":5},{"id":"2512.10016","title":"Latent Action World Models for Control with Unlabeled Trajectories","created":"2025-12-10","cited_by_count":5},{"id":"2604.28169","title":"PhyCo: Learning Controllable Physical Priors for Generative Motion","created":"2026-04-30","cited_by_count":5},{"id":"2603.13770","title":"PhysAlign: Physics-Coherent Image-to-Video Generation through Feature and 3D Representation Alignment","created":"2026-03-14","cited_by_count":4},{"id":"2604.14944","title":"HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments","created":"2026-04-16","cited_by_count":4},{"id":"2605.23878","title":"LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation","created":"2026-05-22","cited_by_count":4},{"id":"2602.04202","title":"VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents","created":"2026-02-04","cited_by_count":3},{"id":"2602.04220","title":"Adaptive 1D Video Diffusion Autoencoder","created":"2026-02-04","cited_by_count":3},{"id":"2605.24962","title":"Tempered Self-Similarity Alignment for Physically Plausible Video Generation","created":"2026-05-24","cited_by_count":1},{"id":"2606.17590","title":"TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization","created":"2026-06-16","cited_by_count":1},{"id":"2606.29940","title":"WARP: Whole-Body Retargeting for Learning from Offline Human Demonstrations","created":"2026-06-29","cited_by_count":1}],"next_cursor":null}