{"list":"other","total":63,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"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":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"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":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2307.05782","title":"Large Language Models","created":"2023-07-11","cited_by_count":780},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2408.14837","title":"Diffusion Models Are Real-Time Game Engines","created":"2024-08-27","cited_by_count":296},{"id":"2405.01434","title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation","created":"2024-05-02","cited_by_count":247},{"id":"1702.00539","title":"Procedural Content Generation via Machine Learning (PCGML)","created":"2017-02-02","cited_by_count":137},{"id":"2501.08325","title":"GameFactory: Creating New Games with Generative Interactive Videos","created":"2025-01-14","cited_by_count":130},{"id":"2411.00769","title":"GameGen-X: Interactive Open-world Game Video Generation","created":"2024-11-01","cited_by_count":128},{"id":"2404.02039","title":"A Survey on Large Language Model-Based Game Agents","created":"2024-04-02","cited_by_count":112},{"id":"2407.16655","title":"MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence","created":"2024-07-23","cited_by_count":89},{"id":"2005.12126","title":"Learning to Simulate Dynamic Environments with GameGAN","created":"2020-05-25","cited_by_count":86},{"id":"2406.09455","title":"Pandora: Towards General World Model with Natural Language Actions and Video States","created":"2024-06-12","cited_by_count":86},{"id":"1805.00728","title":"Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Network","created":"2018-05-02","cited_by_count":76},{"id":"2010.04548","title":"Deep Learning for Procedural Content Generation","created":"2020-10-09","cited_by_count":73},{"id":"2407.08683","title":"SEED-Story: Multimodal Long Story Generation with Large Language Model","created":"2024-07-11","cited_by_count":73},{"id":"2302.05817","title":"Level Generation Through Large Language Models","created":"2023-02-11","cited_by_count":68},{"id":"2302.05981","title":"MarioGPT: Open-Ended Text2Level Generation through Large Language Models","created":"2023-02-12","cited_by_count":64},{"id":"2404.04808","title":"MemFlow: Optical Flow Estimation and Prediction with Memory","created":"2024-04-07","cited_by_count":55},{"id":"2310.02172","title":"Lyfe Agents: Generative agents for low-cost real-time social interactions","created":"2023-10-03","cited_by_count":49},{"id":"2407.12899","title":"DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion","created":"2024-07-17","cited_by_count":47},{"id":"2403.12014","title":"EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents","created":"2024-03-18","cited_by_count":46},{"id":"2310.13255","title":"Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds","created":"2023-10-20","cited_by_count":45},{"id":"2312.09251","title":"VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation","created":"2023-12-14","cited_by_count":41},{"id":"1603.00930","title":"Super Mario as a String: Platformer Level Generation Via LSTMs","created":"2016-03-02","cited_by_count":40},{"id":"2311.11243","title":"AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort","created":"2023-11-19","cited_by_count":38},{"id":"2402.19299","title":"RL-GPT: Integrating Reinforcement Learning and Code-as-policy","created":"2024-02-29","cited_by_count":32},{"id":"2412.00887","title":"Playable Game Generation","created":"2024-12-01","cited_by_count":26},{"id":"2404.08706","title":"Game Generation via Large Language Models","created":"2024-04-11","cited_by_count":25},{"id":"2408.04112","title":"Patchview: LLM-Powered Worldbuilding with Generative Dust and Magnet Visualization","created":"2024-08-07","cited_by_count":23},{"id":"2310.07653","title":"Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models","created":"2023-10-11","cited_by_count":22},{"id":"2305.18243","title":"Practical PCG Through Large Language Models","created":"2023-05-20","cited_by_count":21},{"id":"2308.12915","title":"Language as Reality: A Co-Creative Storytelling Game Experience in 1001 Nights using Generative AI","created":"2023-08-24","cited_by_count":21},{"id":"2404.18919","title":"TheaterGen: Character Management with LLM for Consistent Multi-turn Image Generation","created":"2024-04-29","cited_by_count":19},{"id":"2501.06173","title":"VideoAuteur: Towards Long Narrative Video Generation","created":"2025-01-10","cited_by_count":18},{"id":"1906.05160","title":"General Video Game Rule Generation","created":"2019-06-12","cited_by_count":17},{"id":"2405.07425","title":"Sakuga-42M Dataset: Scaling Up Cartoon Research","created":"2024-05-13","cited_by_count":17},{"id":"1809.02232","title":"Automated Game Design via Conceptual Expansion","created":"2018-09-06","cited_by_count":15},{"id":"2410.18975","title":"Unbounded: A Generative Infinite Game of Character Life Simulation","created":"2024-10-24","cited_by_count":14},{"id":"2403.02454","title":"The Ink Splotch Effect: A Case Study on ChatGPT as a Co-Creative Game Designer","created":"2024-03-04","cited_by_count":12},{"id":"2002.09636","title":"Conceptual Game Expansion","created":"2020-02-22","cited_by_count":11},{"id":"2111.07640","title":"AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment","created":"2021-11-15","cited_by_count":11},{"id":"2211.05709","title":"AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies","created":"2022-11-10","cited_by_count":11},{"id":"2412.04432","title":"Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation","created":"2024-12-05","cited_by_count":9},{"id":"2503.23353","title":"Object Isolated Attention for Consistent Story Visualization","created":"2025-03-30","cited_by_count":7},{"id":"1803.01403","title":"Exploring Novel Game Spaces with Fluidic Games","created":"2018-03-04","cited_by_count":2}],"next_cursor":null}