Interpretability

Vision-Language Models Create Cross-Modal Task Representations ICML 2025 VisRL: Intention-Driven Visual Perception via Reinforced Reasoning ICCV 2025 Visual Agents as Fast and Slow Thinkers ICLR 2025 Visual Analytics for Guiding Feature Attribution Method Selection IJCAI 2025 Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs ICLR 2025 Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clustering IJCNLP 2025 Visualizing token importance for black-box language models AISTATS 2025 Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning ICLR 2025 VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning ICLR 2025 VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow ICCV 2025 VLG-BERT: Towards Better Interpretability in LLMs through Visual and Linguistic Grounding NAACL 2025 Voice Quality Dimensions as Interpretable Primitives for Speaking Style for Atypical Speech and Affect Interspeech 2025 V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models EMNLP 2025 VTimeCoT: Thinking by Drawing for Video Temporal Grounding and Reasoning ICCV 2025 Vulnerability of LLMs to Vertically Aligned Text Manipulations ACL 2025 Wait, that’s not an option: LLMs Robustness with Incorrect Multiple-Choice Options ACL 2025 Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models AAAI 2025 Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations ICLR 2025 Wasserstein Distances, Neuronal Entanglement, and Sparsity ICLR 2025 Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models ACL 2025 Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference NAACL 2025 Weight-of-Thought Reasoning: Exploring Neural Network Weights for Enhanced LLM Reasoning ACL 2025 We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning? ACL 2025 WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation Prediction ICML 2025 What Counts Underlying LLMs’ Moral Dilemma Judgments? ACL 2025