{"list":"other","total":60,"rows":[{"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":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"2206.01714","title":"Compositional Visual Generation with Composable Diffusion Models","created":"2022-06-03","cited_by_count":624},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2211.11158","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","created":"2022-11-21","cited_by_count":312},{"id":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285},{"id":"2302.11552","title":"Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC","created":"2023-02-22","cited_by_count":220},{"id":"2212.08420","title":"Fake it till you make it: Learning transferable representations from synthetic ImageNet clones","created":"2022-12-16","cited_by_count":172},{"id":"2106.13314","title":"Promises and Pitfalls of Black-Box Concept Learning Models","created":"2021-06-24","cited_by_count":131},{"id":"2406.04312","title":"ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization","created":"2024-06-06","cited_by_count":119},{"id":"2105.04289","title":"Do Concept Bottleneck Models Learn as Intended?","created":"2021-05-10","cited_by_count":116},{"id":"2305.16289","title":"Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation","created":"2023-05-25","cited_by_count":100},{"id":"2112.02902","title":"Interpretable Image Classification with Differentiable Prototypes Assignment","created":"2021-12-06","cited_by_count":97},{"id":"2312.07536","title":"FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition","created":"2023-12-12","cited_by_count":91},{"id":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91},{"id":"2011.14340","title":"ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery","created":"2020-11-29","cited_by_count":89},{"id":"2202.01459","title":"Concept Bottleneck Model with Additional Unsupervised Concepts","created":"2022-02-03","cited_by_count":79},{"id":"2311.17002","title":"Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following","created":"2023-11-28","cited_by_count":77},{"id":"2205.15612","title":"GlanceNets: Interpretabile, Leak-proof Concept-based Models","created":"2022-05-31","cited_by_count":73},{"id":"2111.09297","title":"Learning to Compose Visual Relations","created":"2021-11-17","cited_by_count":72},{"id":"2307.05596","title":"Compositional Generalization from First Principles","created":"2023-07-10","cited_by_count":64},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62},{"id":"2209.09056","title":"Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off","created":"2022-09-19","cited_by_count":61},{"id":"2308.06248","title":"FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods","created":"2023-08-11","cited_by_count":50},{"id":"2310.02116","title":"Coarse-to-Fine Concept Bottleneck Models","created":"2023-10-03","cited_by_count":31},{"id":"2411.16725","title":"$\\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models","created":"2024-11-23","cited_by_count":30},{"id":"2301.10367","title":"Towards Robust Metrics for Concept Representation Evaluation","created":"2023-01-25","cited_by_count":29},{"id":"2407.01606","title":"On Discrete Prompt Optimization for Diffusion Models","created":"2024-06-27","cited_by_count":29},{"id":"2407.10910","title":"DataDream: Few-shot Guided Dataset Generation","created":"2024-07-15","cited_by_count":29},{"id":"2411.14982","title":"Large Multi-modal Models Can Interpret Features in Large Multi-modal Models","created":"2024-11-22","cited_by_count":23},{"id":"2211.16080","title":"Understanding and Enhancing Robustness of Concept-based Models","created":"2022-11-29","cited_by_count":22},{"id":"2309.03173","title":"PDiscoNet: Semantically consistent part discovery for fine-grained recognition","created":"2023-09-06","cited_by_count":21},{"id":"2408.02265","title":"Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts","created":"2024-08-05","cited_by_count":20},{"id":"2405.14331","title":"LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision","created":"2024-05-23","cited_by_count":15},{"id":"2405.18217","title":"Understanding Inter-Concept Relationships in Concept-Based Models","created":"2024-05-28","cited_by_count":13},{"id":"2408.02001","title":"AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis","created":"2024-08-04","cited_by_count":12},{"id":"2401.01259","title":"Do Concept Bottleneck Models Respect Localities?","created":"2024-01-02","cited_by_count":10},{"id":"2407.04538","title":"PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers","created":"2024-07-05","cited_by_count":9},{"id":"2412.16086","title":"Towards Interpretable Radiology Report Generation via Concept Bottlenecks using a Multi-Agentic RAG","created":"2024-12-20","cited_by_count":9},{"id":"2503.01145","title":"CoInD: Enabling Logical Compositions in Diffusion Models","created":"2025-03-03","cited_by_count":8},{"id":"2404.14768","title":"Enhancing Prompt Following with Visual Control Through Training-Free Mask-Guided Diffusion","created":"2024-04-23","cited_by_count":6},{"id":"2405.01531","title":"Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models","created":"2024-05-02","cited_by_count":6},{"id":"2402.00912","title":"Can we Constrain Concept Bottleneck Models to Learn Semantically Meaningful Input Features?","created":"2024-02-01","cited_by_count":4}],"next_cursor":null}