{"list":"other","total":79,"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"2312.13286","title":"Generative Multimodal Models are In-Context Learners","created":"2023-12-20","cited_by_count":446},{"id":"2305.14720","title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","created":"2023-05-24","cited_by_count":442},{"id":"2409.11340","title":"OmniGen: Unified Image Generation","created":"2024-09-17","cited_by_count":394},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"2404.14396","title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","created":"2024-04-22","cited_by_count":331},{"id":"2311.10089","title":"Emu Edit: Precise Image Editing via Recognition and Generation Tasks","created":"2023-11-16","cited_by_count":324},{"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":"2306.00986","title":"Diffusion Self-Guidance for Controllable Image Generation","created":"2023-06-01","cited_by_count":305},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297},{"id":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279},{"id":"2305.17216","title":"Generating Images with Multimodal Language Models","created":"2023-05-26","cited_by_count":260},{"id":"2211.12446","title":"EDICT: Exact Diffusion Inversion via Coupled Transformations","created":"2022-11-22","cited_by_count":258},{"id":"2209.00647","title":"Visual Prompting via Image Inpainting","created":"2022-09-01","cited_by_count":250},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212},{"id":"2304.03284","title":"SegGPT: Segmenting Everything In Context","created":"2023-04-06","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":"2301.13670","title":"What Makes Good Examples for Visual In-Context Learning?","created":"2023-01-31","cited_by_count":150},{"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":"2311.16711","title":"LEDITS++: Limitless Image Editing using Text-to-Image Models","created":"2023-11-28","cited_by_count":148},{"id":"2410.13863","title":"Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens","created":"2024-10-17","cited_by_count":147},{"id":"2303.08084","title":"Editing Implicit Assumptions in Text-to-Image Diffusion Models","created":"2023-03-14","cited_by_count":130},{"id":"1705.01088","title":"Visual Attribute Transfer through Deep Image Analogy","created":"2017-05-02","cited_by_count":123},{"id":"2312.05239","title":"SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation","created":"2023-12-08","cited_by_count":110},{"id":"2305.01115","title":"In-Context Learning Unlocked for Diffusion Models","created":"2023-05-01","cited_by_count":104},{"id":"2312.04557","title":"GenTron: Diffusion Transformers for Image and Video Generation","created":"2023-12-07","cited_by_count":82},{"id":"2309.04907","title":"Effective Real Image Editing with Accelerated Iterative Diffusion Inversion","created":"2023-09-10","cited_by_count":79},{"id":"2311.18775","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","created":"2023-11-30","cited_by_count":63},{"id":"2305.16223","title":"Prompt-Free Diffusion: Taking \"Text\" out of Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":62},{"id":"2308.00906","title":"ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation","created":"2023-08-02","cited_by_count":59},{"id":"2311.13601","title":"Visual In-Context Prompting","created":"2023-11-22","cited_by_count":52},{"id":"2308.08947","title":"Watch Your Steps: Local Image and Scene Editing by Text Instructions","created":"2023-08-17","cited_by_count":50},{"id":"2406.15334","title":"Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning","created":"2024-06-21","cited_by_count":50},{"id":"2306.01667","title":"Towards In-context Scene Understanding","created":"2023-06-02","cited_by_count":47},{"id":"2306.08659","title":"Explore In-Context Learning for 3D Point Cloud Understanding","created":"2023-06-14","cited_by_count":40},{"id":"2405.01536","title":"Customizing Text-to-Image Models with a Single Image Pair","created":"2024-05-02","cited_by_count":36},{"id":"2311.16432","title":"Text-Driven Image Editing via Learnable Regions","created":"2023-11-28","cited_by_count":31},{"id":"2311.15657","title":"Enhancing Diffusion Models with Text-Encoder Reinforcement Learning","created":"2023-11-27","cited_by_count":30},{"id":"2405.10316","title":"Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model","created":"2024-05-16","cited_by_count":30},{"id":"2312.03849","title":"LEGO: Learning EGOcentric Action Frame Generation via Visual Instruction Tuning","created":"2023-12-06","cited_by_count":28},{"id":"2307.14331","title":"Visual Instruction Inversion: Image Editing via Visual Prompting","created":"2023-07-26","cited_by_count":26},{"id":"2408.05083","title":"PreciseControl: Enhancing Text-To-Image Diffusion Models with Fine-Grained Attribute Control","created":"2024-07-24","cited_by_count":20},{"id":"2410.13861","title":"PUMA: Empowering Unified MLLM with Multi-granular Visual Generation","created":"2024-10-17","cited_by_count":20},{"id":"2405.15279","title":"Towards Global Optimal Visual In-Context Learning Prompt Selection","created":"2024-05-24","cited_by_count":15},{"id":"2407.10233","title":"Visual Prompt Selection for In-Context Learning Segmentation","created":"2024-07-14","cited_by_count":13},{"id":"2403.09616","title":"Explore In-Context Segmentation via Latent Diffusion Models","created":"2024-03-14","cited_by_count":12},{"id":"2312.01771","title":"IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks","created":"2023-12-04","cited_by_count":10},{"id":"2312.02520","title":"Towards More Unified In-context Visual Understanding","created":"2023-12-05","cited_by_count":10},{"id":"2403.18660","title":"InstructBrush: Learning Attention-based Instruction Optimization for Image Editing","created":"2024-03-27","cited_by_count":10},{"id":"2404.18459","title":"Chameleon: A Data-Efficient Generalist for Dense Visual Prediction in the Wild","created":"2024-04-29","cited_by_count":6},{"id":"2404.07603","title":"GLID: Pre-training a Generalist Encoder-Decoder Vision Model","created":"2024-04-11","cited_by_count":5},{"id":"2406.11262","title":"Generative Visual Instruction Tuning","created":"2024-06-17","cited_by_count":4}],"next_cursor":null}