interpretability

Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large p ICML 2025 A Classification View on Meta Learning Bandits ICML 2025 An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks ICML 2025 A Theory of Learning with Autoregressive Chain of Thought COLT 2025 Causal Invariance-aware Augmentation for Brain Graph Contrastive Learning ICML 2025 CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations ICML 2025 Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders ICML 2025 COMRECGC: Global Graph Counterfactual Explainer through Common Recourse ICML 2025 Concept-Based Unsupervised Domain Adaptation ICML 2025 Conformal Prediction as Bayesian Quadrature ICML 2025 DCBM: Data-Efficient Visual Concept Bottleneck Models ICML 2025 Direct Motion Models for Assessing Generated Videos ICML 2025 Divide and Conquer: Exploring Language-centric Tree Reasoning for Video Question-Answering ICML 2025 ECG-Byte: A Tokenizer for End-to-End Generative Electrocardiogram Language Modeling MLHC 2025 Enhancing Performance of Explainable AI Models with Constrained Concept Refinement ICML 2025 Feature Shift Localization Network ICML 2025 Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages ICML 2025 From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection ICML 2025 GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation ICML 2025 GRAIL: Graph Edit Distance and Node Alignment using LLM-Generated Code ICML 2025 Human Cognition-Inspired Hierarchical Fuzzy Learning Machine ICML 2025 Improving ARDS Diagnosis Through Context-Aware Concept Bottleneck Models MLHC 2025 Improving Soft Unification with Knowledge Graph Embedding Methods ICML 2025 InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory ICML 2025 Inner Information Analysis Algorithm for Deep Neural Network based on Community ICLR 2025