{"total":82,"rows":[{"id":"2310.12508","title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","created":"2023-10-19","cited_by_count":386,"area":"diffusion"},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376,"area":"alignment"},{"id":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285,"area":null},{"id":"2304.04934","title":"Model Sparsity Can Simplify Machine Unlearning","created":"2023-04-11","cited_by_count":214,"area":"safety"},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2111.09805","title":"DICE: Leveraging Sparsification for Out-of-Distribution Detection","created":"2021-11-18","cited_by_count":166,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114,"area":null},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82,"area":null},{"id":"2112.01008","title":"Editing a classifier by rewriting its prediction rules","created":"2021-12-02","cited_by_count":65,"area":null},{"id":"2408.01432","title":"VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance","created":"2024-07-18","cited_by_count":65,"area":null},{"id":"2201.10766","title":"A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes","created":"2022-01-26","cited_by_count":56,"area":null},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2306.12517","title":"FFCV: Accelerating Training by Removing Data Bottlenecks","created":"2023-06-21","cited_by_count":49,"area":null},{"id":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2305.19164","title":"LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images","created":"2023-05-30","cited_by_count":46,"area":null},{"id":"2511.13653","title":"Weight-sparse transformers have interpretable circuits","created":"2025-11-17","cited_by_count":44,"area":"mechinterp"},{"id":"2205.03295","title":"The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2212.04871","title":"Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet","created":"2022-12-09","cited_by_count":41,"area":null},{"id":"2204.08945","title":"Missingness Bias in Model Debugging","created":"2022-04-19","cited_by_count":38,"area":null},{"id":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2203.02013","title":"DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations","created":"2022-03-03","cited_by_count":34,"area":null},{"id":"2106.03805","title":"3DB: A Framework for Debugging Computer Vision Models","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2310.02116","title":"Coarse-to-Fine Concept Bottleneck Models","created":"2023-10-03","cited_by_count":31,"area":null},{"id":"2211.12491","title":"ModelDiff: A Framework for Comparing Learning Algorithms","created":"2022-11-22","cited_by_count":30,"area":null},{"id":"2106.12447","title":"How Well do Feature Visualizations Support Causal Understanding of CNN Activations?","created":"2021-06-23","cited_by_count":28,"area":null},{"id":"2503.23283","title":"Language Guided Concept Bottleneck Models for Interpretable Continual Learning","created":"2025-03-30","cited_by_count":28,"area":null},{"id":"2309.17430","title":"FACTS: First Amplify Correlations and Then Slice to Discover Bias","created":"2023-09-29","cited_by_count":26,"area":null},{"id":"2308.10782","title":"Sparse Linear Concept Discovery Models","created":"2023-08-21","cited_by_count":22,"area":null},{"id":"2209.07592","title":"Explicit Tradeoffs between Adversarial and Natural Distributional Robustness","created":"2022-09-15","cited_by_count":20,"area":null},{"id":"2405.06855","title":"Linear Explanations for Individual Neurons","created":"2024-05-10","cited_by_count":19,"area":null},{"id":"2307.05471","title":"Scale Alone Does not Improve Mechanistic Interpretability in Vision Models","created":"2023-07-11","cited_by_count":18,"area":"mechinterp"},{"id":"2407.03921","title":"Concept Bottleneck Models Without Predefined Concepts","created":"2024-07-04","cited_by_count":17,"area":null},{"id":"2203.15566","title":"Core Risk Minimization using Salient ImageNet","created":"2022-03-28","cited_by_count":15,"area":null},{"id":"2312.14452","title":"How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection?","created":"2023-12-22","cited_by_count":15,"area":null},{"id":"2504.19774","title":"If Concept Bottlenecks are the Question, are Foundation Models the Answer?","created":"2025-04-28","cited_by_count":15,"area":null},{"id":"2212.02648","title":"Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases","created":"2022-12-05","cited_by_count":13,"area":null},{"id":"2206.09868","title":"Understanding Robust Learning through the Lens of Representation Similarities","created":"2022-06-20","cited_by_count":12,"area":null},{"id":"2502.20134","title":"Show and Tell: Visually Explainable Deep Neural Nets via Spatially-Aware Concept Bottleneck Models","created":"2025-02-27","cited_by_count":12,"area":null},{"id":"2404.03323","title":"Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning","created":"2024-04-04","cited_by_count":11,"area":null},{"id":"2211.10370","title":"Invariant Learning via Diffusion Dreamed Distribution Shifts","created":"2022-11-18","cited_by_count":10,"area":null},{"id":"2312.13839","title":"Q-SENN: Quantized Self-Explaining Neural Networks","created":"2023-12-21","cited_by_count":9,"area":null},{"id":"2110.03804","title":"FOCUS: Familiar Objects in Common and Uncommon Settings","created":"2021-10-07","cited_by_count":8,"area":null},{"id":"2303.13166","title":"Take 5: Interpretable Image Classification with a Handful of Features","created":"2023-03-23","cited_by_count":7,"area":null},{"id":"2307.04317","title":"Text Descriptions are Compressive and Invariant Representations for Visual Learning","created":"2023-07-10","cited_by_count":7,"area":null},{"id":"2406.18534","title":"Towards Compositionality in Concept Learning","created":"2024-06-26","cited_by_count":7,"area":null},{"id":"2502.15809","title":"Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition","created":"2025-02-19","cited_by_count":7,"area":"mllm"},{"id":"2211.10024","title":"Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks","created":"2022-11-18","cited_by_count":6,"area":null},{"id":"2409.02882","title":"Benchmarking Spurious Bias in Few-Shot Image Classifiers","created":"2024-09-04","cited_by_count":6,"area":null},{"id":"2206.13498","title":"Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior","created":"2022-06-27","cited_by_count":5,"area":null},{"id":"2207.04104","title":"Towards a More Rigorous Science of Blindspot Discovery in Image Classification Models","created":"2022-07-08","cited_by_count":5,"area":null},{"id":"2306.00183","title":"Diffused Redundancy in Pre-trained Representations","created":"2023-05-31","cited_by_count":5,"area":"mechinterp"},{"id":"2408.04471","title":"What could go wrong? Discovering and describing failure modes in computer vision","created":"2024-08-08","cited_by_count":5,"area":null},{"id":"2207.02518","title":"Compositional Generalization in Grounded Language Learning via Induced Model Sparsity","created":"2022-07-06","cited_by_count":4,"area":null},{"id":"2209.08647","title":"Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness","created":"2022-09-18","cited_by_count":4,"area":null},{"id":"2409.10504","title":"DILA: Dictionary Label Attention for Mechanistic Interpretability in High-dimensional Multi-label Medical Coding Prediction","created":"2024-09-16","cited_by_count":4,"area":"mechinterp"},{"id":"2603.07343","title":"Learning Concept Bottleneck Models from Mechanistic Explanations","created":"2026-03-07","cited_by_count":4,"area":null},{"id":"2211.09859","title":"Data-Centric Debugging: mitigating model failures via targeted data collection","created":"2022-11-17","cited_by_count":3,"area":null},{"id":"2301.13845","title":"Interpreting Robustness Proofs of Deep Neural Networks","created":"2023-01-31","cited_by_count":3,"area":null},{"id":"2312.05464","title":"Identifying and Mitigating Model Failures through Few-shot CLIP-aided Diffusion Generation","created":"2023-12-09","cited_by_count":3,"area":null},{"id":"2507.01722","title":"When Does Pruning Benefit Vision Representations?","created":"2025-07-02","cited_by_count":3,"area":null},{"id":"2602.01322","title":"PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding","created":"2026-02-01","cited_by_count":3,"area":"mechinterp"},{"id":"2308.06686","title":"TorchQL: A Programming Framework for Integrity Constraints in Machine Learning","created":"2023-08-13","cited_by_count":2,"area":null},{"id":"2310.04519","title":"SPADE: Sparsity-Guided Debugging for Deep Neural Networks","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2502.20130","title":"QPM: Discrete Optimization for Globally Interpretable Image Classification","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2503.06730","title":"Adaptive Test-Time Intervention for Concept Bottleneck Models","created":"2025-03-09","cited_by_count":2,"area":null},{"id":"2505.22199","title":"Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision Layer","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2511.03725","title":"Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition","created":"2025-11-05","cited_by_count":2,"area":null},{"id":"2603.05629","title":"Rethinking Concept Bottleneck Models: From Pitfalls to Solutions","created":"2026-03-05","cited_by_count":2,"area":"lr"},{"id":"2605.20612","title":"Matryoshka Concept Bottleneck Models","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2310.06221","title":"Detecting and Learning Out-of-Distribution Data in the Open world: Algorithm and Theory","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2311.01655","title":"Detecting Spurious Correlations via Robust Visual Concepts in Real and AI-Generated Image Classification","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2404.18976","title":"Foundations of Multisensory Artificial Intelligence","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2504.12197","title":"Beyond Patches: Mining Interpretable Part-Prototypes for Explainable AI","created":"2025-04-16","cited_by_count":1,"area":null},{"id":"2504.13140","title":"PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition","created":"2025-04-17","cited_by_count":1,"area":null},{"id":"2604.02468","title":"Hierarchical, Interpretable, Label-Free Concept Bottleneck Model","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2310.07184","title":"NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2510.21998","title":"From Black-box to Causal-box: Towards Building More Interpretable Models","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2510.23253","title":"A Video Is Not Worth a Thousand Words","created":"2025-10-27","cited_by_count":0,"area":"mllm"},{"id":"2604.14519","title":"CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2607.17861","title":"ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulation","created":"2026-07-20","cited_by_count":0,"area":null}],"next_cursor":null}