firstbacksecondback
31 Results
|
Poster
|
Fri 11:00 |
Finding Transformer Circuits With Edge Pruning Adithya Bhaskar · Alexander Wettig · Dan Friedman · Danqi Chen |
|
|
Workshop
|
Self-Attention Limits Working Memory Capacity of Transformer-Based Models Dongyu Gong · Hantao Zhang |
||
|
Poster
|
Wed 16:30 |
Algorithmic Capabilities of Random Transformers Ziqian Zhong · Jacob Andreas |
|
|
Poster
|
Fri 16:30 |
Abrupt Learning in Transformers: A Case Study on Matrix Completion Pulkit Gopalani · Ekdeep S Lubana · Wei Hu |
|
|
Workshop
|
Structure Development in List Sorting Transformers Einar Urdshals · Jasmina Urdshals |
||
|
Workshop
|
Words in Motion: Interpreting Motion Forecasting Transformers by Controlling Representations Omer Sahin Tas · Royden Wagner |
||
|
Poster
|
Thu 16:30 |
Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models Jack Merullo · Carsten Eickhoff · Ellie Pavlick |
|
|
Poster
|
Wed 16:30 |
Symmetry Discovery Beyond Affine Transformations Ben Shaw · Abram Magner · Kevin Moon |
|
|
Affinity Event
|
Tue 14:20 |
SignAttention: On the Interpretability of Transformer Models for Sign Language Translation Pedro Alejandro Dal Bianco |
|
|
Workshop
|
Interpreting Transformers for Jet Tagging Aaron Wang · Abhijith Gandrakota · Elham E Khoda · Vivekanand Gyanchand Sahu · Javier Duarte · Priyansh Bhatnagar · Jennifer Ngadiuba |
||
|
Poster
|
Wed 11:00 |
Interpretable Image Classification with Adaptive Prototype-based Vision Transformers Chiyu Ma · Jon Donnelly · Wenjun Liu · Soroush Vosoughi · Cynthia Rudin · Chaofan Chen |
|
|
Poster
|
Fri 11:00 |
Learning to Understand: Identifying Interactions via the Möbius Transform Justin Kang · Yigit Efe Erginbas · Landon Butler · Ramtin Pedarsani · Kannan Ramchandran |