{"total":22,"rows":[{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79,"area":null},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2405.15325","title":"On the Identification of Temporally Causal Representation with Instantaneous Dependence","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2406.18400","title":"Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers","created":"2024-06-26","cited_by_count":15,"area":null},{"id":"2410.23501","title":"All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling","created":"2024-10-30","cited_by_count":14,"area":null},{"id":"2503.08980","title":"I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?","created":"2025-03-12","cited_by_count":13,"area":null},{"id":"2504.11609","title":"Towards Interpretable Deep Generative Models via Causal Representation Learning","created":"2025-04-15","cited_by_count":13,"area":null},{"id":"2410.23620","title":"Identifiability Guarantees for Causal Disentanglement from Purely Observational Data","created":"2024-10-31","cited_by_count":7,"area":null},{"id":"2501.12500","title":"Learning General Causal Structures with Hidden Dynamic Process for Climate Analysis","created":"2025-01-21","cited_by_count":7,"area":null},{"id":"2405.16083","title":"From Orthogonality to Dependency: Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals","created":"2024-05-25","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":"2502.12603","title":"Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series Forecasting","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2502.21123","title":"Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2410.11444","title":"A Theoretical Survey on Foundation Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2502.16637","title":"Time Series Domain Adaptation via Latent Invariant Causal Mechanism","created":"2025-02-23","cited_by_count":1,"area":null},{"id":"2505.07180","title":"Causal View of Time Series Imputation: Some Identification Results on Missing Mechanism","created":"2025-05-12","cited_by_count":1,"area":null},{"id":"2507.04754","title":"Intervening to Learn and Compose Causally Disentangled Representations","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2511.01932","title":"Deciphering Personalization: Towards Fine-Grained Explainability in Natural Language for Personalized Image Generation Models","created":"2025-11-02","cited_by_count":1,"area":null},{"id":"2602.11118","title":"A Doubly Robust Machine Learning Approach for Disentangling Treatment Effect Heterogeneity with Functional Outcomes","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2602.24275","title":"Hierarchical Action Learning for Weakly-Supervised Action Segmentation","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2605.02640","title":"Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2509.07946","title":"Bringing Multi-Modal Multi-Task Federated Foundation Models to Education Domain: Prospects and Challenges","created":"2025-09-09","cited_by_count":0,"area":null}],"next_cursor":null}