{"list":"other","total":52,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"2301.07525","title":"OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation","created":"2023-01-18","cited_by_count":326},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297},{"id":"2409.04429","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","created":"2024-09-06","cited_by_count":295},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195},{"id":"2406.08451","title":"GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices","created":"2024-06-12","cited_by_count":194},{"id":"2310.01218","title":"Making LLaMA SEE and Draw with SEED Tokenizer","created":"2023-10-02","cited_by_count":185},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"2306.04181","title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","created":"2023-06-07","cited_by_count":172},{"id":"2408.02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","created":"2024-08-05","cited_by_count":150},{"id":"2311.01361","title":"GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks","created":"2023-11-02","cited_by_count":119},{"id":"2405.04007","title":"SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing","created":"2024-05-07","cited_by_count":97},{"id":"2402.16641","title":"Towards Open-ended Visual Quality Comparison","created":"2024-02-26","cited_by_count":85},{"id":"2306.00973","title":"Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models","created":"2023-06-01","cited_by_count":77},{"id":"2407.08683","title":"SEED-Story: Multimodal Long Story Generation with Large Language Model","created":"2024-07-11","cited_by_count":73},{"id":"2405.07364","title":"BoQ: A Place is Worth a Bag of Learnable Queries","created":"2024-05-12","cited_by_count":64},{"id":"2210.08477","title":"Large-scale Text-to-Image Generation Models for Visual Artists' Creative Works","created":"2022-10-16","cited_by_count":61},{"id":"2406.12742","title":"Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning","created":"2024-06-18","cited_by_count":54},{"id":"2104.05845","title":"Visual Goal-Step Inference using wikiHow","created":"2021-04-12","cited_by_count":43},{"id":"2407.13773","title":"OpenDataLab: Empowering General Artificial Intelligence with Open Datasets","created":"2024-06-04","cited_by_count":29},{"id":"2406.14643","title":"Holistic Evaluation for Interleaved Text-and-Image Generation","created":"2024-06-20","cited_by_count":28},{"id":"2310.07749","title":"OpenLEAF: Open-Domain Interleaved Image-Text Generation and Evaluation","created":"2023-10-11","cited_by_count":16},{"id":"2408.14468","title":"K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences","created":"2024-08-26","cited_by_count":16},{"id":"2102.04033","title":"A Hybrid Bandit Model with Visual Priors for Creative Ranking in Display Advertising","created":"2021-02-08","cited_by_count":15},{"id":"2407.00087","title":"ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedback","created":"2024-06-25","cited_by_count":13},{"id":"2109.01839","title":"Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark","created":"2021-09-04","cited_by_count":12},{"id":"2201.05194","title":"Reverse-Engineering Information Presentations: Recovering Hierarchical Grouping from Layouts of Visual Elements","created":"2022-01-13","cited_by_count":4}],"next_cursor":null}