firstbacksecondback
109 Results
|
Poster
|
Wed 2:30 |
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models Asma Ghandeharioun · Avi Caciularu · Adam Pearce · Lucas Dixon · Mor Geva |
|
|
Poster
|
Thu 4:30 |
SIN: Selective and Interpretable Normalization for Long-Term Time Series Forecasting Lu Han · Han-Jia Ye · De-Chuan Zhan |
|
|
Poster
|
Thu 4:30 |
Improving Interpretation Faithfulness for Vision Transformers Lijie Hu · Yixin Liu · Ninghao Liu · Mengdi Huai · Lichao Sun · Di Wang |
|
|
Poster
|
Thu 4:30 |
Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation Floris Holstege · Bram Wouters · Noud van Giersbergen · Cees Diks |
|
|
Poster
|
Wed 2:30 |
Attribution-based Explanations that Provide Recourse Cannot be Robust Hidde Fokkema · Rianne de Heide · Tim van Erven |
|
|
Poster
|
Tue 4:30 |
Attribute Based Interpretable Evaluation Metrics for Generative Models Dongkyun Kim · Mingi Kwon · Youngjung Uh |
|
|
Poster
|
Wed 2:30 |
Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks Haoyu Li · Shichang Zhang · Longwen Tang · Mathieu Bauchy · Yizhou Sun |
|
|
Poster
|
Wed 4:30 |
Attention Meets Post-hoc Interpretability: A Mathematical Perspective Gianluigi Lopardo · Frederic Precioso · Damien Garreau |
|
|
Poster
|
Wed 2:30 |
Faithfulness Measurable Masked Language Models Andreas Madsen · Siva Reddy · Sarath Chandar |
|
|
Poster
|
Tue 2:30 |
Using AI Uncertainty Quantification to Improve Human Decision-Making Laura Marusich · Jonathan Bakdash · Yan Zhou · Murat Kantarcioglu |
|
|
Poster
|
Wed 4:30 |
On the Tractability of SHAP Explanations under Markovian Distributions Reda Marzouk · De la Higuera |
|
|
Poster
|
Wed 4:30 |
Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation Xuexin Chen · Ruichu Cai · Zhengting Huang · Yuxuan Zhu · Julien Horwood · Zhifeng Hao · Zijian Li · Jose Miguel Hernandez-Lobato |