{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"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":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"1902.10178","title":"Unmasking Clever Hans Predictors and Assessing What Machines Really Learn","created":"2019-02-26","cited_by_count":365},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"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":"1703.03717","title":"Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations","created":"2017-03-10","cited_by_count":294},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293},{"id":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285},{"id":"2001.05371","title":"Making deep neural networks right for the right scientific reasons by interacting with their explanations","created":"2020-01-15","cited_by_count":142},{"id":"2106.13314","title":"Promises and Pitfalls of Black-Box Concept Learning Models","created":"2021-06-24","cited_by_count":131},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119},{"id":"2104.14403","title":"Do Feature Attribution Methods Correctly Attribute Features?","created":"2021-04-27","cited_by_count":98},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98},{"id":"2011.12854","title":"Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations","created":"2020-11-25","cited_by_count":94},{"id":"2012.00893","title":"Evaluating Explanations: How much do explanations from the teacher aid students?","created":"2020-12-01","cited_by_count":94},{"id":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85},{"id":"2202.01459","title":"Concept Bottleneck Model with Additional Unsupervised Concepts","created":"2022-02-03","cited_by_count":79},{"id":"1706.04156","title":"Gradient descent GAN optimization is locally stable","created":"2017-06-13","cited_by_count":67},{"id":"2305.19951","title":"Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts","created":"2023-05-31","cited_by_count":63},{"id":"2209.11222","title":"Concept Activation Regions: A Generalized Framework For Concept-Based Explanations","created":"2022-09-22","cited_by_count":57},{"id":"2304.14068","title":"Interpretable Neural-Symbolic Concept Reasoning","created":"2023-04-27","cited_by_count":57},{"id":"2311.14125","title":"Scalable AI Safety via Doubly-Efficient Debate","created":"2023-11-23","cited_by_count":57},{"id":"2303.17071","title":"DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents","created":"2023-03-30","cited_by_count":52},{"id":"2305.07722","title":"In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making","created":"2023-05-12","cited_by_count":50},{"id":"2404.08978","title":"Incremental Residual Concept Bottleneck Models","created":"2024-04-13","cited_by_count":43},{"id":"2108.12099","title":"Learning to Give Checkable Answers with Prover-Verifier Games","created":"2021-08-27","cited_by_count":32},{"id":"2310.02116","title":"Coarse-to-Fine Concept Bottleneck Models","created":"2023-10-03","cited_by_count":31},{"id":"2405.16507","title":"Causal Concept Graph Models: Beyond Causal Opacity in Deep Learning","created":"2024-05-26","cited_by_count":29},{"id":"2302.02876","title":"Variational Information Pursuit for Interpretable Predictions","created":"2023-02-06","cited_by_count":25},{"id":"2412.05152","title":"Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation","created":"2024-12-06","cited_by_count":25},{"id":"2309.08395","title":"Learning by Self-Explaining","created":"2023-09-15","cited_by_count":17},{"id":"2407.15527","title":"Interpretable Concept-Based Memory Reasoning","created":"2024-07-22","cited_by_count":17},{"id":"2503.04363","title":"Causally Reliable Concept Bottleneck Models","created":"2025-03-06","cited_by_count":17},{"id":"2504.19774","title":"If Concept Bottlenecks are the Question, are Foundation Models the Answer?","created":"2025-04-28","cited_by_count":15},{"id":"2406.09949","title":"Neural Concept Binder","created":"2024-06-14","cited_by_count":14},{"id":"2011.13986","title":"Reflective-Net: Learning from Explanations","created":"2020-11-27","cited_by_count":13},{"id":"2310.11884","title":"From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks","created":"2023-10-18","cited_by_count":13},{"id":"2502.11245","title":"Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens","created":"2025-02-16","cited_by_count":13},{"id":"2403.17410","title":"On permutation-invariant neural networks","created":"2024-03-26","cited_by_count":10},{"id":"2505.24492","title":"Object Centric Concept Bottlenecks","created":"2025-05-30","cited_by_count":10},{"id":"2206.00759","title":"Interpretability Guarantees with Merlin-Arthur Classifiers","created":"2022-06-01","cited_by_count":9},{"id":"2405.15722","title":"Models That Prove Their Own Correctness","created":"2024-05-24","cited_by_count":7},{"id":"2506.02092","title":"Towards Better Generalization and Interpretability in Unsupervised Concept-Based Models","created":"2025-06-02","cited_by_count":1}],"next_cursor":null}