ICLR 2025 Workshop XAI4Science Submissions

Scaling Sparse Autoencoders for Interpreting Protein Structure Prediction
John Jingxuan Yang, David J Yang, Nithin Parsan
- Published: 06 Mar 2025, Last Modified: 06 Mar 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
TIME-AWARE FEATURE SELECTION: ADAPTIVE TEMPORAL MASKING FOR STABLE SPARSE AUTOENCODER TRAINING
Ed Li, Junyu Ren
- Published: 06 Mar 2025, Last Modified: 20 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Measuring Leakage in Concept-Based Methods: An Information Theoretic Approach
Mikael Makonnen, Moritz Vandenhirtz, Sonia Laguna, Julia E Vogt
- Published: 06 Mar 2025, Last Modified: 13 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
LENS: Learning and Evolving Numerical Scores for Cohort-Specific Clinical Insights
Kei Sen Fong, Mehul Motani
- Published: 06 Mar 2025, Last Modified: 20 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation
Hyeongwon Jang, Changhun Kim, Eunho Yang
- Published: 06 Mar 2025, Last Modified: 14 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
AlphaGo or beta-hCG: a reinforcement learning framework for assisted conception
Simon Hanassab, Elizaveta Sheremetyeva, Sonali Parbhoo, Scott Nelson, Professor Waljit Dhillo, Thomas Heinis, Ali Abbara
- Published: 06 Mar 2025, Last Modified: 12 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
From Markov to Laplace: How Mamba In-Context Learns Markov Chains
Marco Bondaschi, Nived Rajaraman, Xiuying Wei, Kannan Ramchandran, Razvan Pascanu, Caglar Gulcehre, Michael Gastpar, Ashok Vardhan Makkuva
- Published: 06 Mar 2025, Last Modified: 10 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Piecewise Polynomial Regression of Tame Functions via Integer Programming
Gilles Bareilles, Johannes Aspman, Jiří Němeček, Jakub Marecek
- Published: 06 Mar 2025, Last Modified: 09 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Generating $\pi$-Functional Molecules Using STGG+ with Active Learning
Alexia Jolicoeur-Martineau, Yan Zhang, Boris Knyazev, Aristide Baratin, Cheng-Hao Liu
- Published: 06 Mar 2025, Last Modified: 08 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Bayesian Concept Bottleneck Models with LLM Priors
Jean Feng, Avni Kothari, Lucas Zier, Chandan Singh, Yan Shuo Tan
- Published: 06 Mar 2025, Last Modified: 19 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations
Thomas Decker, Volker Tresp, Florian Buettner
- Published: 06 Mar 2025, Last Modified: 14 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Modeling Multi-Regional and Non-Stationary Neural Dynamics via Latent Sub-Circuits
Noga Mudrik, Ryan Ly, Oliver Ruebel, Adam Shabti Charles
- Published: 06 Mar 2025, Last Modified: 17 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Moment Neural Operator: Interpretable mapping in discontinuous function spaces
Qi Gao, Kuang Huang, Xuan Di
- Published: 06 Mar 2025, Last Modified: 18 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
BarkXAI: A Lightweight Post-Hoc Explainable Method for Tree Species Classification with Quantifiable Concepts
Yunmei Huang, Songlin Hou, Zachary Nelson Horve, Songlin Fei
- Published: 06 Mar 2025, Last Modified: 20 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis
Rachel S.Y. Teo, Tan Minh Nguyen
- Published: 06 Mar 2025, Last Modified: 06 Mar 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Skip the Equations: Learning Behavior of Personalized Dynamical Systems Directly From Data
Krzysztof Kacprzyk, Julianna Piskorz, Mihaela van der Schaar
- Published: 06 Mar 2025, Last Modified: 20 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
LEARNING MULTIPHASE AND MULTIPHYSICS SYSTEM WITH DECOUPLED STATE SPACE MODEL
Yun Young Choi, Seunghwan Lee, Minho Lee, Lee JinHaeng, Joohwan Ko, Chanwoong Moon
- Published: 06 Mar 2025, Last Modified: 20 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding
Hesam Hosseini, Ghazal Hosseini Mighan, Amirabbas Afzali, Sajjad Amini, Amir Houmansadr
- Published: 06 Mar 2025, Last Modified: 18 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Graph Discrete Diffusion: a Spectral Study
Olga Zaghen, Manuel Madeira, Laura Toni, Pascal Frossard
- Published: 06 Mar 2025, Last Modified: 11 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Spatially-Informed Sampling Enables Accurate Prediction of Large-Scale Mutational Effects
Maxime Basse, Dianzhuo Wang, Eugene Shakhnovich
- Published: 06 Mar 2025, Last Modified: 06 Mar 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Causally Reliable Concept Bottleneck Models
Giovanni De Felice, Arianna Casanova, Francesco De Santis, Silvia Santini, Johannes Schneider, Pietro Barbiero, Alberto Termine
- Published: 06 Mar 2025, Last Modified: 18 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Circuit mechanism for compositional induction in transformer
Cheng Tang, Brenden Lake, Mehrdad Jazayeri
- Published: 06 Mar 2025, Last Modified: 18 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation
Leander Weber, Jim Berend, Moritz Weckbecker, Alexander Binder, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
- Published: 06 Mar 2025, Last Modified: 15 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
SHAP-BASED A-POSTERIORI INTERPRETABILITY FOR GRAPH NEURAL NETWORKS IN CFD-BASED SUSTAINABLE BUILDING SIMULATIONS
BO SUN, hanmo wang, Tam Hong Nguyen, Alexander Lin
- Published: 06 Mar 2025, Last Modified: 14 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
Bartosz Cywiński, Kamil Deja
- Published: 06 Mar 2025, Last Modified: 14 Apr 2025
- ICLR 2025 Workshop XAI4Science
- Readers: Everyone