{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400},{"id":"2411.04983","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","created":"2024-11-07","cited_by_count":386},{"id":"2206.10498","title":"PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change","created":"2022-06-21","cited_by_count":382},{"id":"2311.04145","title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","created":"2023-11-07","cited_by_count":350},{"id":"2311.17918","title":"Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving","created":"2023-11-29","cited_by_count":319},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2210.06407","title":"Interactive Language: Talking to Robots in Real Time","created":"2022-10-12","cited_by_count":218},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"2504.00983","title":"WorldScore: A Unified Evaluation Benchmark for World Generation","created":"2025-04-01","cited_by_count":156},{"id":"2410.07166","title":"Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making","created":"2024-10-09","cited_by_count":144},{"id":"2406.04520","title":"NATURAL PLAN: Benchmarking LLMs on Natural Language Planning","created":"2024-06-06","cited_by_count":128},{"id":"2502.20694","title":"WorldModelBench: Judging Video Generation Models As World Models","created":"2025-02-28","cited_by_count":124},{"id":"2105.08756","title":"Pathdreamer: A World Model for Indoor Navigation","created":"2021-05-18","cited_by_count":118},{"id":"2007.00394","title":"The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose","created":"2020-07-01","cited_by_count":95},{"id":"1907.01172","title":"Procedure Planning in Instructional Videos","created":"2019-07-02","cited_by_count":92},{"id":"2403.02622","title":"World Models for Autonomous Driving: An Initial Survey","created":"2024-03-05","cited_by_count":80},{"id":"2403.00504","title":"Learning and Leveraging World Models in Visual Representation Learning","created":"2024-03-01","cited_by_count":72},{"id":"2502.11831","title":"Intuitive physics understanding emerges from self-supervised pretraining on natural videos","created":"2025-02-17","cited_by_count":70},{"id":"2205.02300","title":"P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision","created":"2022-05-04","cited_by_count":52},{"id":"2402.08178","title":"LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents","created":"2024-02-13","cited_by_count":51},{"id":"2310.03249","title":"Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning","created":"2023-10-05","cited_by_count":49},{"id":"2109.04869","title":"PlaTe: Visually-Grounded Planning with Transformers in Procedural Tasks","created":"2021-09-10","cited_by_count":45},{"id":"2406.08407","title":"MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos","created":"2024-06-12","cited_by_count":43},{"id":"2303.14676","title":"PDPP: Projected Diffusion for Procedure Planning in Instructional Videos","created":"2023-03-26","cited_by_count":36},{"id":"2312.11782","title":"Learning Object State Changes in Videos: An Open-World Perspective","created":"2023-12-19","cited_by_count":36},{"id":"2304.09179","title":"Pretrained Language Models as Visual Planners for Human Assistance","created":"2023-04-17","cited_by_count":28},{"id":"2502.13092","title":"Text2World: Benchmarking Large Language Models for Symbolic World Model Generation","created":"2025-02-18","cited_by_count":26},{"id":"2403.01599","title":"SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos","created":"2024-03-03","cited_by_count":24},{"id":"2305.14879","title":"ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games","created":"2023-05-24","cited_by_count":23},{"id":"2308.08885","title":"Event-Guided Procedure Planning from Instructional Videos with Text Supervision","created":"2023-08-17","cited_by_count":21},{"id":"2310.00608","title":"Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning","created":"2023-10-01","cited_by_count":14},{"id":"2409.20557","title":"Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos","created":"2024-09-30","cited_by_count":12},{"id":"2411.08794","title":"LLM-Based World Models Can Make Decisions Solely, But Rigorous Evaluations are Needed","created":"2024-11-13","cited_by_count":10},{"id":"2311.09064","title":"Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models","created":"2023-11-15","cited_by_count":6},{"id":"2405.18193","title":"In-Context Symmetries: Self-Supervised Learning through Contextual World Models","created":"2024-05-28","cited_by_count":5},{"id":"2407.05119","title":"Open-Event Procedure Planning in Instructional Videos","created":"2024-07-06","cited_by_count":3}],"next_cursor":null}