{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"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":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727},{"id":"1701.07875","title":"Wasserstein GAN","created":"2017-01-26","cited_by_count":639},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"1806.00069","title":"Explaining Explanations: An Overview of Interpretability of Machine Learning","created":"2018-05-31","cited_by_count":508},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"2010.16061","title":"Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation","created":"2020-10-11","cited_by_count":425},{"id":"1812.08951","title":"Analysis Methods in Neural Language Processing: A Survey","created":"2018-12-21","cited_by_count":277},{"id":"1604.04562","title":"A Network-based End-to-End Trainable Task-oriented Dialogue System","created":"2016-04-15","cited_by_count":252},{"id":"2210.04885","title":"What the DAAM: Interpreting Stable Diffusion Using Cross Attention","created":"2022-10-10","cited_by_count":236},{"id":"1310.4375","title":"Fast Computation of Wasserstein Barycenters","created":"2013-10-16","cited_by_count":216},{"id":"2001.06216","title":"GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks","created":"2020-01-17","cited_by_count":209},{"id":"1708.08296","title":"Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models","created":"2017-08-28","cited_by_count":206},{"id":"2309.17102","title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models","created":"2023-09-29","cited_by_count":185},{"id":"1712.09923","title":"What do we need to build explainable AI systems for the medical domain?","created":"2017-12-28","cited_by_count":129},{"id":"2403.12036","title":"One-Step Image Translation with Text-to-Image Models","created":"2024-03-18","cited_by_count":116},{"id":"2001.03447","title":"Explaining the Explainer: A First Theoretical Analysis of LIME","created":"2020-01-10","cited_by_count":89},{"id":"2312.10893","title":"The Metacognitive Demands and Opportunities of Generative AI","created":"2023-12-18","cited_by_count":87},{"id":"1807.02910","title":"Model Agnostic Supervised Local Explanations","created":"2018-07-09","cited_by_count":83},{"id":"2306.09316","title":"Diffusion Models for Open-Vocabulary Segmentation","created":"2023-06-15","cited_by_count":64},{"id":"2312.10113","title":"Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation","created":"2023-12-15","cited_by_count":62},{"id":"2403.04014","title":"PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement","created":"2024-03-06","cited_by_count":62},{"id":"2007.12391","title":"Artificial Intelligence in the Creative Industries: A Review","created":"2020-07-24","cited_by_count":61},{"id":"2106.07875","title":"S-LIME: Stabilized-LIME for Model Explanation","created":"2021-06-15","cited_by_count":52},{"id":"2406.14555","title":"A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models","created":"2024-06-20","cited_by_count":52},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52},{"id":"2012.03058","title":"BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations","created":"2020-12-05","cited_by_count":51},{"id":"2210.09292","title":"Efficient Diffusion Models for Vision: A Survey","created":"2022-10-07","cited_by_count":51},{"id":"1909.02437","title":"ALIME: Autoencoder Based Approach for Local Interpretability","created":"2019-09-04","cited_by_count":41},{"id":"2006.06091","title":"Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies","created":"2020-06-10","cited_by_count":41},{"id":"1806.07498","title":"Defining Locality for Surrogates in Post-hoc Interpretablity","created":"2018-06-19","cited_by_count":33},{"id":"2311.16432","title":"Text-Driven Image Editing via Learnable Regions","created":"2023-11-28","cited_by_count":31},{"id":"2402.17403","title":"Sora Generates Videos with Stunning Geometrical Consistency","created":"2024-02-27","cited_by_count":31},{"id":"2006.05714","title":"OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms","created":"2020-06-10","cited_by_count":30},{"id":"2109.08438","title":"TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models","created":"2021-09-17","cited_by_count":28},{"id":"2212.08044","title":"Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift","created":"2022-12-15","cited_by_count":24},{"id":"2305.03509","title":"Diffusion Explainer: Visual Explanation for Text-to-image Stable Diffusion","created":"2023-05-04","cited_by_count":17},{"id":"2402.01787","title":"Harm Amplification in Text-to-Image Models","created":"2024-02-01","cited_by_count":15},{"id":"2306.15774","title":"Next Steps for Human-Centered Generative AI: A Technical Perspective","created":"2023-06-27","cited_by_count":13},{"id":"2309.04372","title":"MoEController: Instruction-based Arbitrary Image Manipulation with Mixture-of-Expert Controllers","created":"2023-09-08","cited_by_count":12},{"id":"2407.06182","title":"Compositional Video Generation as Flow Equalization","created":"2024-06-10","cited_by_count":12},{"id":"2405.05852","title":"Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control","created":"2024-05-09","cited_by_count":11},{"id":"2311.07286","title":"Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanations","created":"2023-11-13","cited_by_count":8},{"id":"2403.07706","title":"Fast and Simple Explainability for Point Cloud Networks","created":"2024-03-12","cited_by_count":6},{"id":"2409.18214","title":"Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey","created":"2024-09-26","cited_by_count":6},{"id":"2406.16272","title":"Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement","created":"2024-06-24","cited_by_count":5},{"id":"2410.15374","title":"Explainability of Point Cloud Neural Networks Using SMILE: Statistical Model-Agnostic Interpretability with Local Explanations","created":"2024-10-20","cited_by_count":4},{"id":"2108.04371","title":"Extending LIME for Business Process Automation","created":"2021-08-09","cited_by_count":3},{"id":"2312.04780","title":"Fine-Tuning InstructPix2Pix for Advanced Image Colorization","created":"2023-12-08","cited_by_count":1}],"next_cursor":null}