{"list":"other","total":92,"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":"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"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":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1506.03365","title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop","created":"2015-06-10","cited_by_count":1355},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2306.09341","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","created":"2023-06-15","cited_by_count":890},{"id":"1912.11035","title":"CNN-generated images are surprisingly easy to spot... for now","created":"2019-12-23","cited_by_count":847},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2305.01937","title":"Can Large Language Models Be an Alternative to Human Evaluations?","created":"2023-05-03","cited_by_count":734},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2311.04257","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","created":"2023-11-07","cited_by_count":547},{"id":"2003.08685","title":"Leveraging Frequency Analysis for Deep Fake Image Recognition","created":"2020-03-19","cited_by_count":504},{"id":"2302.10174","title":"Towards Universal Fake Image Detectors that Generalize Across Generative Models","created":"2023-02-20","cited_by_count":490},{"id":"2303.09295","title":"DIRE for Diffusion-Generated Image Detection","created":"2023-03-16","cited_by_count":390},{"id":"2210.14896","title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","created":"2022-10-26","cited_by_count":379},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"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":"2306.08571","title":"GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image","created":"2023-06-14","cited_by_count":321},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316},{"id":"2204.14217","title":"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers","created":"2022-04-28","cited_by_count":307},{"id":"2211.00680","title":"On the detection of synthetic images generated by diffusion models","created":"2022-11-01","cited_by_count":283},{"id":"2008.10588","title":"What makes fake images detectable? Understanding properties that generalize","created":"2020-08-24","cited_by_count":273},{"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":"2002.00133","title":"Global Texture Enhancement for Fake Face Detection in the Wild","created":"2020-02-01","cited_by_count":220},{"id":"2108.00941","title":"A Survey of Human-in-the-loop for Machine Learning","created":"2021-08-02","cited_by_count":215},{"id":"2304.04370","title":"OpenAGI: When LLM Meets Domain Experts","created":"2023-04-10","cited_by_count":197},{"id":"2210.06998","title":"DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models","created":"2022-10-13","cited_by_count":168},{"id":"2312.00195","title":"Raising the Bar of AI-generated Image Detection with CLIP","created":"2023-11-30","cited_by_count":164},{"id":"2311.06783","title":"Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models","created":"2023-11-12","cited_by_count":152},{"id":"2306.04717","title":"AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment","created":"2023-06-07","cited_by_count":142},{"id":"2104.02617","title":"Are GAN generated images easy to detect? A critical analysis of the state-of-the-art","created":"2021-04-06","cited_by_count":139},{"id":"2103.05630","title":"ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis","created":"2021-03-09","cited_by_count":126},{"id":"2401.17879","title":"AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error","created":"2024-01-31","cited_by_count":125},{"id":"2311.12397","title":"PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection","created":"2023-11-21","cited_by_count":122},{"id":"2402.04614","title":"Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models","created":"2024-02-07","cited_by_count":105},{"id":"2305.17306","title":"Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance","created":"2023-05-26","cited_by_count":102},{"id":"2402.19091","title":"Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection","created":"2024-02-29","cited_by_count":89},{"id":"2203.13964","title":"Fusing Global and Local Features for Generalized AI-Synthesized Image Detection","created":"2022-03-26","cited_by_count":88},{"id":"2303.14126","title":"CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images","created":"2023-03-24","cited_by_count":84},{"id":"2402.00045","title":"Detecting Multimedia Generated by Large AI Models: A Survey","created":"2024-01-22","cited_by_count":76},{"id":"2112.01573","title":"FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization","created":"2021-12-02","cited_by_count":71},{"id":"2304.13023","title":"Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images","created":"2023-04-25","cited_by_count":66},{"id":"2401.08276","title":"AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception","created":"2024-01-16","cited_by_count":65},{"id":"2402.00126","title":"Common Sense Reasoning for Deepfake Detection","created":"2024-01-31","cited_by_count":65},{"id":"2311.17138","title":"Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now","created":"2023-11-28","cited_by_count":61},{"id":"2105.06496","title":"Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowds","created":"2021-05-13","cited_by_count":58},{"id":"2310.15150","title":"Online Detection of AI-Generated Images","created":"2023-10-23","cited_by_count":55},{"id":"2304.12489","title":"Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detection","created":"2023-04-24","cited_by_count":50},{"id":"2307.16545","title":"Towards General Visual-Linguistic Face Forgery Detection","created":"2023-07-31","cited_by_count":45},{"id":"2310.05590","title":"Perceptual Artifacts Localization for Image Synthesis Tasks","created":"2023-10-09","cited_by_count":43},{"id":"2403.10854","title":"A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment","created":"2024-03-16","cited_by_count":43},{"id":"2007.12909","title":"CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis","created":"2020-07-25","cited_by_count":42},{"id":"2312.02896","title":"BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models","created":"2023-12-05","cited_by_count":41},{"id":"2107.05821","title":"Detect and Locate: Exposing Face Manipulation by Semantic- and Noise-level Telltales","created":"2021-07-13","cited_by_count":39},{"id":"2304.11670","title":"Evading DeepFake Detectors via Adversarial Statistical Consistency","created":"2023-04-23","cited_by_count":37},{"id":"2312.08880","title":"GenDet: Towards Good Generalizations for AI-Generated Image Detection","created":"2023-12-12","cited_by_count":36},{"id":"2207.13744","title":"Lighting (In)consistency of Paint by Text","created":"2022-07-27","cited_by_count":35},{"id":"2206.14617","title":"Perspective (In)consistency of Paint by Text","created":"2022-06-27","cited_by_count":34},{"id":"2207.09679","title":"Explaining Deepfake Detection by Analysing Image Matching","created":"2022-07-20","cited_by_count":34},{"id":"2304.06470","title":"Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes","created":"2023-03-29","cited_by_count":31},{"id":"2402.11843","title":"WildFake: A Large-scale Challenging Dataset for AI-Generated Images Detection","created":"2024-02-19","cited_by_count":31},{"id":"2106.09369","title":"Wavelet-Packets for Deepfake Image Analysis and Detection","created":"2021-06-17","cited_by_count":25},{"id":"2211.08615","title":"GLFF: Global and Local Feature Fusion for AI-synthesized Image Detection","created":"2022-11-16","cited_by_count":25},{"id":"2106.07226","title":"More Real than Real: A Study on Human Visual Perception of Synthetic Faces","created":"2021-06-14","cited_by_count":23},{"id":"2312.05476","title":"Exploring the Naturalness of AI-Generated Images","created":"2023-12-09","cited_by_count":22},{"id":"2402.01162","title":"2AFC Prompting of Large Multimodal Models for Image Quality Assessment","created":"2024-02-02","cited_by_count":20},{"id":"2306.02776","title":"Cheap-fake Detection with LLM using Prompt Engineering","created":"2023-06-05","cited_by_count":15},{"id":"2311.15556","title":"PKU-I2IQA: An Image-to-Image Quality Assessment Database for AI Generated Images","created":"2023-11-27","cited_by_count":14},{"id":"2302.14475","title":"Benchmarking Deepart Detection","created":"2023-02-28","cited_by_count":12},{"id":"2311.02692","title":"ChEF: A Comprehensive Evaluation Framework for Standardized Assessment of Multimodal Large Language Models","created":"2023-11-05","cited_by_count":9}],"next_cursor":null}