|
Poster
|
Tue 4:30
|
AND: Audio Network Dissection for Interpreting Deep Acoustic Models
Tung-Yu Wu · Yu-Xiang Lin · Lily Weng
|
|
|
Poster
|
Thu 2:30
|
Viewing Transformers Through the Lens of Long Convolutions Layers
Itamar Zimerman · Lior Wolf
|
|
|
Poster
|
Wed 4:30
|
Learning a Diffusion Model Policy from Rewards via Q-Score Matching
Michael Psenka · Alejandro Escontrela · Pieter Abbeel · Yi Ma
|
|
|
Poster
|
Thu 4:30
|
Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
Wenhan Yang · Jingdong Gao · Baharan Mirzasoleiman
|
|
|
Poster
|
Tue 2:30
|
Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift
Benjamin Eyre · Elliot Creager · David Madras · Vardan Papyan · Richard Zemel
|
|
|
Poster
|
Wed 2:30
|
How Learning by Reconstruction Produces Uninformative Features For Perception
Randall Balestriero · Yann LeCun
|
|
|
Poster
|
Tue 2:30
|
TabLog: Test-Time Adaptation for Tabular Data Using Logic Rules
Weijieying Ren · Xiaoting Li · Huiyuan Chen · Vineeth Rakesh · Zhuoyi Wang · Mahashweta Das · Vasant Honavar
|
|
|
Poster
|
Wed 4:30
|
Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras
Tzu-Yuan Lin · Minghan Zhu · Maani Ghaffari
|
|
|
Poster
|
Tue 4:30
|
Slot Abstractors: Toward Scalable Abstract Visual Reasoning
Shanka Subhra Mondal · Jonathan Cohen · Taylor Webb
|
|
|
Poster
|
Thu 2:30
|
Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time
Sungyoon Kim · Mert Pilanci
|
|
|
Poster
|
Wed 4:30
|
Prompting a Pretrained Transformer Can Be a Universal Approximator
Aleksandar Petrov · Phil Torr · Adel Bibi
|
|
|
Poster
|
Thu 4:30
|
Towards Certified Unlearning for Deep Neural Networks
Binchi Zhang · Yushun Dong · Tianhao Wang · Jundong Li
|
|
