{"list":"other","total":72,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"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":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"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":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"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":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403},{"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":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"2310.10639","title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","created":"2023-10-16","cited_by_count":269},{"id":"2209.00647","title":"Visual Prompting via Image Inpainting","created":"2022-09-01","cited_by_count":250},{"id":"2212.06909","title":"Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting","created":"2022-12-13","cited_by_count":233},{"id":"2210.06407","title":"Interactive Language: Talking to Robots in Real Time","created":"2022-10-12","cited_by_count":218},{"id":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212},{"id":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206},{"id":"2302.11550","title":"Scaling Robot Learning with Semantically Imagined Experience","created":"2023-02-22","cited_by_count":177},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164},{"id":"2310.08576","title":"Learning to Act from Actionless Videos through Dense Correspondences","created":"2023-10-12","cited_by_count":164},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142},{"id":"1702.00539","title":"Procedural Content Generation via Machine Learning (PCGML)","created":"2017-02-02","cited_by_count":137},{"id":"1805.07914","title":"Imitating Latent Policies from Observation","created":"2018-05-21","cited_by_count":101},{"id":"1610.04286","title":"Sim-to-Real Robot Learning from Pixels with Progressive Nets","created":"2016-10-13","cited_by_count":94},{"id":"2309.07906","title":"Generative Image Dynamics","created":"2023-09-14","cited_by_count":94},{"id":"1612.08810","title":"The Predictron: End-To-End Learning and Planning","created":"2016-12-28","cited_by_count":93},{"id":"2307.06940","title":"Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation","created":"2023-07-13","cited_by_count":90},{"id":"1709.07592","title":"Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks","created":"2017-09-22","cited_by_count":89},{"id":"2005.12126","title":"Learning to Simulate Dynamic Environments with GameGAN","created":"2020-05-25","cited_by_count":86},{"id":"1806.10729","title":"Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation","created":"2018-06-28","cited_by_count":81},{"id":"2305.14343","title":"Video Prediction Models as Rewards for Reinforcement Learning","created":"2023-05-23","cited_by_count":78},{"id":"2312.09187","title":"Vision-Language Models as a Source of Rewards","created":"2023-12-14","cited_by_count":66},{"id":"1911.13071","title":"Increasing Generality in Machine Learning through Procedural Content Generation","created":"2019-11-29","cited_by_count":59},{"id":"2206.11898","title":"Score-based Generative Models for Calorimeter Shower Simulation","created":"2022-06-17","cited_by_count":52},{"id":"2210.13435","title":"Dichotomy of Control: Separating What You Can Control from What You Cannot","created":"2022-10-24","cited_by_count":47},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44},{"id":"1807.10366","title":"Robot Motion Planning in Learned Latent Spaces","created":"2018-07-26","cited_by_count":42},{"id":"2306.07257","title":"MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images","created":"2023-06-12","cited_by_count":42},{"id":"2312.07322","title":"GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos","created":"2023-12-12","cited_by_count":40},{"id":"2402.04764","title":"Code as Reward: Empowering Reinforcement Learning with VLMs","created":"2024-02-07","cited_by_count":39},{"id":"2205.10816","title":"Chain of Thought Imitation with Procedure Cloning","created":"2022-05-22","cited_by_count":30},{"id":"2306.01872","title":"Probabilistic Adaptation of Text-to-Video Models","created":"2023-06-02","cited_by_count":29},{"id":"1806.09655","title":"Learning what you can do before doing anything","created":"2018-06-25","cited_by_count":26},{"id":"2003.10520","title":"Neural Game Engine: Accurate learning of generalizable forward models from pixels","created":"2020-03-23","cited_by_count":12},{"id":"2206.12396","title":"Text-Driven Stylization of Video Objects","created":"2022-06-24","cited_by_count":12}],"next_cursor":null}