Interpretability

Physics Aware Neural Networks for Unsupervised Binding Energy Prediction ICML 2025 Physics-Informed Generative Modeling of Wireless Channels ICML 2025 PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition Residuals ICML 2025 Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis EMNLP 2025 Pioneering Explainable Video Fact-Checking with a New Dataset and Multi-role Multimodal Model Approach AAAI 2025 Pioneer: Physics-informed Riemannian Graph ODE for Entropy-increasing Dynamics AAAI 2025 Pixel-level Certified Explanations via Randomized Smoothing ICML 2025 Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts EMNLP 2025 PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning ICML 2025 PledgeTracker: A System for Monitoring the Fulfilment of Pledges EMNLP 2025 Polarity inversion operators in PLM CoNLL 2025 Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs EMNLP 2025 POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality CVPR 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: A Theory of Deep Learning Must Include Compositional Sparsity ICML 2025 Position-aware Automatic Circuit Discovery ACL 2025 Position: Deep Learning is Not So Mysterious or Different ICML 2025 Position: Explainable AI Cannot Advance Without Better User Studies ICML 2025 Position: Rethinking Explainable Machine Learning as Applied Statistics ICML 2025 Position: We Can’t Understand AI Using our Existing Vocabulary ICML 2025 Position: We Need An Algorithmic Understanding of Generative AI ICML 2025 Potemkin Understanding in Large Language Models ICML 2025 Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation Criteria ACL 2025