{"list":"other","total":91,"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"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":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"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":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"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":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2006.06676","title":"Training Generative Adversarial Networks with Limited Data","created":"2020-06-11","cited_by_count":1186},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1611.04076","title":"Least Squares Generative Adversarial Networks","created":"2016-11-13","cited_by_count":1001},{"id":"2201.11793","title":"Denoising Diffusion Restoration Models","created":"2022-01-27","cited_by_count":963},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"1612.02177","title":"Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring","created":"2016-12-07","cited_by_count":727},{"id":"1808.04560","title":"Deep Retinex Decomposition for Low-Light Enhancement","created":"2018-08-14","cited_by_count":723},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"2401.16420","title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","created":"2024-01-29","cited_by_count":326},{"id":"2311.10089","title":"Emu Edit: Precise Image Editing via Recognition and Generation Tasks","created":"2023-11-16","cited_by_count":324},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280},{"id":"2309.14181","title":"Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision","created":"2023-09-25","cited_by_count":249},{"id":"2212.06909","title":"Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting","created":"2022-12-13","cited_by_count":233},{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220},{"id":"2402.17525","title":"Diffusion Model-Based Image Editing: A Survey","created":"2024-02-27","cited_by_count":212},{"id":"2303.11950","title":"Learning A Sparse Transformer Network for Effective Image Deraining","created":"2023-03-21","cited_by_count":205},{"id":"2404.09990","title":"HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing","created":"2024-04-15","cited_by_count":193},{"id":"2309.17102","title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models","created":"2023-09-29","cited_by_count":185},{"id":"2312.06739","title":"SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models","created":"2023-12-11","cited_by_count":177},{"id":"2001.06816","title":"Human-Aware Motion Deblurring","created":"2020-01-19","cited_by_count":175},{"id":"2402.03766","title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","created":"2024-02-06","cited_by_count":174},{"id":"2303.09618","title":"HIVE: Harnessing Human Feedback for Instructional Visual Editing","created":"2023-03-16","cited_by_count":173},{"id":"2309.03895","title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","created":"2023-09-07","cited_by_count":164},{"id":"2212.04489","title":"SINE: SINgle Image Editing with Text-to-Image Diffusion Models","created":"2022-12-08","cited_by_count":159},{"id":"2404.06512","title":"InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD","created":"2024-04-09","cited_by_count":159},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153},{"id":"2402.05935","title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","created":"2024-02-08","cited_by_count":131},{"id":"2210.05475","title":"GENIE: Higher-Order Denoising Diffusion Solvers","created":"2022-10-11","cited_by_count":127},{"id":"1904.02904","title":"Dense Haze: A benchmark for image dehazing with dense-haze and haze-free images","created":"2019-04-05","cited_by_count":107},{"id":"2212.04711","title":"ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal","created":"2022-12-09","cited_by_count":103},{"id":"2305.04441","title":"Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models","created":"2023-05-08","cited_by_count":99},{"id":"2304.03994","title":"RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors","created":"2023-04-08","cited_by_count":73},{"id":"2108.02934","title":"From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data","created":"2021-08-06","cited_by_count":68},{"id":"2305.18047","title":"InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User Instructions","created":"2023-05-29","cited_by_count":64},{"id":"2304.10244","title":"Omni Aggregation Networks for Lightweight Image Super-Resolution","created":"2023-04-20","cited_by_count":62},{"id":"2211.16582","title":"SinDDM: A Single Image Denoising Diffusion Model","created":"2022-11-29","cited_by_count":60},{"id":"2303.13132","title":"Masked Image Training for Generalizable Deep Image Denoising","created":"2023-03-23","cited_by_count":57},{"id":"2310.02426","title":"EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods","created":"2023-10-03","cited_by_count":54},{"id":"2401.12503","title":"Small Language Model Meets with Reinforced Vision Vocabulary","created":"2024-01-23","cited_by_count":43},{"id":"2210.09477","title":"UniTune: Text-Driven Image Editing by Fine Tuning a Diffusion Model on a Single Image","created":"2022-10-17","cited_by_count":42},{"id":"2112.12089","title":"Reflash Dropout in Image Super-Resolution","created":"2021-12-22","cited_by_count":41},{"id":"2310.13165","title":"CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation","created":"2023-10-19","cited_by_count":41},{"id":"2308.03867","title":"From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal","created":"2023-08-07","cited_by_count":39},{"id":"2012.07616","title":"WDNet: Watermark-Decomposition Network for Visible Watermark Removal","created":"2020-12-14","cited_by_count":37},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32},{"id":"2302.06098","title":"Towards Local Visual Modeling for Image Captioning","created":"2023-02-13","cited_by_count":26},{"id":"2312.06738","title":"InstructAny2Pix: Flexible Visual Editing via Multimodal Instruction Following","created":"2023-12-11","cited_by_count":25},{"id":"2208.12526","title":"Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning","created":"2022-08-26","cited_by_count":22},{"id":"2402.07398","title":"VisLingInstruct: Elevating Zero-Shot Learning in Multi-Modal Language Models with Autonomous Instruction Optimization","created":"2024-02-12","cited_by_count":16},{"id":"2305.17489","title":"Text-to-image Editing by Image Information Removal","created":"2023-05-27","cited_by_count":12},{"id":"2312.08984","title":"CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer","created":"2023-12-14","cited_by_count":10},{"id":"2309.05451","title":"Dual-view Curricular Optimal Transport for Cross-lingual Cross-modal Retrieval","created":"2023-09-11","cited_by_count":9},{"id":"2407.16198","title":"INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model","created":"2024-07-23","cited_by_count":4},{"id":"2303.03472","title":"Structured Kernel Estimation for Photon-Limited Deconvolution","created":"2023-03-06","cited_by_count":2}],"next_cursor":null}