interpretability

Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations ICML 2025 Learning Soft Sparse Shapes for Efficient Time-Series Classification ICML 2025 MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-text Decoding ICML 2025 Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization ICLR 2025 Mixture of Experts Made Intrinsically Interpretable ICML 2025 Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery ICML 2025 Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional Data ICML 2025 Physics-Informed Generative Modeling of Wireless Channels ICML 2025 Position: AI Scaling: From Up to Down and Out ICML 2025 Position: AI’s growing due process problem ICML 2025 Position: AI Should Not Be An Imitation Game: Centaur Evaluations ICML 2025 Position: We Can’t Understand AI Using our Existing Vocabulary ICML 2025 SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability ICML 2025 SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders ICML 2025 SAE-V: Interpreting Multimodal Models for Enhanced Alignment ICML 2025 Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups ICML 2025 The Logical Implication Steering Method for Conditional Interventions on Transformer Generation ICML 2025 TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration ICML 2025 Towards an Explainable Comparison and Alignment of Feature Embeddings ICML 2025 What makes an Ensemble (Un) Interpretable? ICML 2025 A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity ICML 2024 Analysis of Transformers for Medical Image Retrieval MIDL 2024 A Unified View of FANOVA: A Comprehensive Bayesian Framework for Component Selection and Estimation ICML 2024 Automated Statistical Model Discovery with Language Models ICML 2024 Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension ICML 2024