NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
39 results for “keyword:"dictionary learning"” in ICLR 2027. 4 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]De-Absorption Reparameterization: Post-hoc Repair of Feature Absorption in Sparse Autoencoders.▲3.0k2.33
[PDF]Exploring Divergence Between Brain Responses and Language Model Representations Using Crosscoders▲9.2k2.67
[PDF]AtomShare: One Shared Atom Set Across a Mixture-of-Experts Stack for Budget-Constrained Weight Compression▼71.25
[PDF]Cross-Architecture Universal SAEs: A Shared Sparse Dictionary for Vision and Diffusion Transformers▼1351.33
[PDF]Where Does the Verbalizable Workspace Band Begin? An Audit of the Jacobian-Lens Instruments Across Open-Weight Families▲14k3.00
[PDF]An Identifiability Hierarchy for Mechanistic Interpretability: Interpretability Claims Live at Different Levels of Identifiability▼1351.33
[PDF]How Optimality Structures Sparse Dictionaries: Theory for Interpreting SAE Representations▲5.4k3.00
[PDF]Data-driven Random-feature Approximation of Koopman Generators of Nonlinear Continuous-time Systems▼4.3k2.00
[PDF]Underdetermined Polytopic Matrix Factorization: Identifiability via Determinant Maximization and Face-Span Geometry▼1.2k3.00
[PDF]NAMED FROM THE START: CONCEPT-ANCHORED SPARSE AUTOENCODERS FOR INTERPRETABILITY OF VISION-LANGUAGE MODELS▲11k2.00
[PDF]Beyond Retraining Stability: Auditing Duplication Dependence in Vision Sparse Autoencoders▼12k1.67
[PDF]Training Selects Among Behaviorally Equivalent Computations in In-Context Dictionary Learning▲5.4k3.00
[PDF]Evaluating Semantic State Response and Generated Visual Feedback under Distinct Input Contracts▼1351.33
[PDF]BOLD-MoE: Base-Optimized Learning of Orthogonal Dictionaries for Mixture-of-Experts Compression▼5.8k2.33
[PDF]When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders▼1.2k3.00
[PDF]Weight-Dictionary Decomposition: Reading a Transformer's Residual Stream with Its Own Writes▼1351.33