{"total":92,"rows":[{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109,"area":null},{"id":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41,"area":null},{"id":"2503.01776","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2306.17638","title":"Geometric Autoencoders -- What You See is What You Decode","created":"2023-06-30","cited_by_count":23,"area":null},{"id":"2107.11191","title":"Regularising Inverse Problems with Generative Machine Learning Models","created":"2021-07-22","cited_by_count":22,"area":null},{"id":"2203.06514","title":"Sparsity and Heterogeneous Dropout for Continual Learning in the Null Space of Neural Activations","created":"2022-03-12","cited_by_count":19,"area":null},{"id":"2305.13175","title":"Discovering Universal Geometry in Embeddings with ICA","created":"2023-05-22","cited_by_count":19,"area":null},{"id":"2106.02923","title":"Local Disentanglement in Variational Auto-Encoders Using Jacobian $L_1$ Regularization","created":"2021-06-05","cited_by_count":17,"area":null},{"id":"2407.03921","title":"Concept Bottleneck Models Without Predefined Concepts","created":"2024-07-04","cited_by_count":17,"area":null},{"id":"2204.05133","title":"On the link between conscious function and general intelligence in humans and machines","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2112.13896","title":"Two Sparsities Are Better Than One: Unlocking the Performance Benefits of Sparse-Sparse Networks","created":"2021-12-27","cited_by_count":15,"area":null},{"id":"2501.05855","title":"ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2507.23221","title":"A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations","created":"2025-07-31","cited_by_count":9,"area":null},{"id":"2109.10656","title":"Vehicle Behavior Prediction and Generalization Using Imbalanced Learning Techniques","created":"2021-09-22","cited_by_count":7,"area":null},{"id":"2206.03698","title":"What do we learn? Debunking the Myth of Unsupervised Outlier Detection","created":"2022-06-08","cited_by_count":6,"area":null},{"id":"2506.13060","title":"Rethinking Explainability in the Era of Multimodal AI","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2509.05291","title":"Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining","created":"2025-09-05","cited_by_count":6,"area":null},{"id":"2103.14528","title":"Model-based Reconstruction with Learning: From Unsupervised to Supervised and Beyond","created":"2021-03-26","cited_by_count":5,"area":null},{"id":"2503.15573","title":"Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2505.21364","title":"Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2506.02204","title":"BehaviorBox: Automated Discovery of Fine-Grained Performance Differences Between Language Models","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2509.24510","title":"Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2107.10030","title":"Differentiable Feature Selection, a Reparameterization Approach","created":"2021-07-21","cited_by_count":4,"area":null},{"id":"2208.10847","title":"Latent Variable Models in the Era of Industrial Big Data: Extension and Beyond","created":"2022-08-23","cited_by_count":4,"area":null},{"id":"2405.14270","title":"Sparse $L^1$-Autoencoders for Scientific Data Compression","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2408.03388","title":"A Non-negative VAE:the Generalized Gamma Belief Network","created":"2024-08-06","cited_by_count":4,"area":null},{"id":"2410.06993","title":"Efficient Distribution Matching of Representations via Noise-Injected Deep InfoMax","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2412.16247","title":"Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models","created":"2024-12-20","cited_by_count":4,"area":null},{"id":"2505.11388","title":"The Future is Sparse: Embedding Compression for Scalable Retrieval in Recommender Systems","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2605.29889","title":"Where Do Apparent LLM Clinical Triage Failures Arise? Localizing the Multiple-Choice Format Effect","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2103.07674","title":"Efficient Sparse Artificial Neural Networks","created":"2021-03-13","cited_by_count":3,"area":null},{"id":"2112.09214","title":"Sparse Coding with Multi-Layer Decoders using Variance Regularization","created":"2021-12-16","cited_by_count":3,"area":null},{"id":"2511.16309","title":"Sparse Autoencoders are Topic Models","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2306.12627","title":"Targeted collapse regularized autoencoder for anomaly detection: black hole at the center","created":"2023-06-22","cited_by_count":2,"area":null},{"id":"2309.01532","title":"Are We Using Autoencoders in a Wrong Way?","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2312.06229","title":"Tackling Cyberattacks through AI-based Reactive Systems: A Holistic Review and Future Vision","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2501.00089","title":"Insights on Galaxy Evolution from Interpretable Sparse Feature Networks","created":"2024-12-30","cited_by_count":2,"area":null},{"id":"2510.23749","title":"Re-envisioning Euclid Galaxy Morphology: Identifying and Interpreting Features with Sparse Autoencoders","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2601.04768","title":"LANGSAE EDITING: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2603.04981","title":"Rethinking Representativeness and Diversity in Dynamic Data Selection","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2606.26228","title":"Interpreting \"Interpretability\" and Explaining \"Explainability\" in Machine Learning in Physics","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2102.07503","title":"One-shot learning for the long term: consolidation with an artificial hippocampal algorithm","created":"2021-02-15","cited_by_count":1,"area":null},{"id":"2112.11920","title":"List Autoencoder: Towards Deep Learning Based Reliable Transmission Over Noisy Channels","created":"2021-12-19","cited_by_count":1,"area":null},{"id":"2302.02979","title":"Learning disentangled representations for explainable chest X-ray classification using Dirichlet VAEs","created":"2023-02-06","cited_by_count":1,"area":null},{"id":"2404.17651","title":"Hard ASH: Sparsity and the right optimizer make a continual learner","created":"2024-04-26","cited_by_count":1,"area":null},{"id":"2502.18644","title":"Steered Generation via Gradient Descent on Sparse Features","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2503.21608","title":"Nonlinear Multiple Response Regression and Learning of Latent Spaces","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2504.20667","title":"Explanations Go Linear: Post-hoc Explainability for Tabular Data with Interpretable Meta-Encoding","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2505.11576","title":"Concept-Guided Interpretability via Neural Chunking","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2510.25512","title":"FaCT: Faithful Concept Traces for Explaining Neural Network Decisions","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2604.11749","title":"HistLens: Mapping Idea Change across Concepts and Corpora","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.12809","title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.12289","title":"The Standard Interpretable Model: A general theory of interpretable machine learning to deductively design interpretable methods using Lagrangian mechanics","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2609.01936","title":"Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2101.11376","title":"Learning Abstract Representations through Lossy Compression of Multi-Modal Signals","created":"2021-01-27","cited_by_count":0,"area":null},{"id":"2102.00315","title":"Metalearning: Sparse Variable-Structure Automata","created":"2021-01-30","cited_by_count":0,"area":null},{"id":"2104.06593","title":"A Semi-Supervised Classification Method of Apicomplexan Parasites and Host Cell Using Contrastive Learning Strategy","created":"2021-04-14","cited_by_count":0,"area":null},{"id":"2201.09065","title":"Online Attentive Kernel-Based Temporal Difference Learning","created":"2022-01-22","cited_by_count":0,"area":null},{"id":"2205.11126","title":"KRNet: Towards Efficient Knowledge Replay","created":"2022-05-23","cited_by_count":0,"area":null},{"id":"2209.04425","title":"The Role Of Biology In Deep Learning","created":"2022-09-07","cited_by_count":0,"area":null},{"id":"2302.09363","title":"Autocodificadores Variacionales (VAE) Fundamentos Te\\'oricos y Aplicaciones","created":"2023-02-18","cited_by_count":0,"area":null},{"id":"2304.00935","title":"Learning Sparsity of Representations with Discrete Latent Variables","created":"2023-04-03","cited_by_count":0,"area":null},{"id":"2308.13722","title":"Time-to-Pattern: Information-Theoretic Unsupervised Learning for Scalable Time Series Summarization","created":"2023-08-26","cited_by_count":0,"area":null},{"id":"2406.05598","title":"Understanding Inhibition Through Maximally Tense Images","created":"2024-06-08","cited_by_count":0,"area":null},{"id":"2407.13685","title":"Beyond Trend Following: Deep Learning for Market Trend Prediction","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2408.09967","title":"Unsupervised Machine Learning Hybrid Approach Integrating Linear Programming in Loss Function: A Robust Optimization Technique","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2504.11170","title":"A real-time anomaly detection method for robots based on a flexible and sparse latent space","created":"2025-04-15","cited_by_count":0,"area":null},{"id":"2505.23917","title":"Representational Difference Explanations","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2507.02322","title":"Neural Network-based Study for Rice Leaf Disease Recognition and Classification: A Comparative Analysis Between Feature-based Model and Direct Imaging Model","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2507.10106","title":"BlueGlass: A Framework for Composite AI Safety","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2507.22832","title":"Pulling Back the Curtain on Deep Networks","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2507.23600","title":"EB-gMCR: Energy-Based Generative Modeling for Signal Unmixing and Multivariate Curve Resolution","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2509.00131","title":"Self-supervised large-scale kidney abnormality detection in drug safety assessment studies","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2510.01252","title":"GPT and Prejudice: A Sparse Approach to Understanding Learned Representations in Large Language Models","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2603.03131","title":"Joint Training Across Multiple Activation Sparsity Regimes","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2604.01619","title":"Automatic Image-Level Morphological Trait Annotation for Organismal Images","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.08298","title":"What Cohort INRs Encode and Where to Freeze Them","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.22472","title":"Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.31304","title":"Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.03695","title":"Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.07646","title":"DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.08324","title":"Set-Based Transformer for Atmospheric Compensation in Standoff LWIR Hyperspectral Imaging","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2607.24706","title":"SADe: Sparse-Atom Support Decontamination for Few-Shot Segmentation with Weak Support Annotations","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.04057","title":"LaPrune: Controllable Differentiable Sparsity at Million Scale","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.06912","title":"Fast LapSum: Exact Differentiable Top-$k$ at Million Scale","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.15632","title":"Sparse Prototype Code Underlies Classification and Prediction Across Modalities","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.16927","title":"Hierarchical Data Selection via Manifold Coverage and Sparse Feature Coverage in LLM Post-training","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.05174","title":"SMILE: Self-Explainable Multimodal Information Bottleneck for Medical Diagnosis","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.08585","title":"Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.35351","title":"Interference Beyond Geometry in Concept Extraction","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}