|
Poster
|
Fri 7:30
|
Differentiable Euler Characteristic Transforms for Shape Classification
Ernst Roell · Bastian Rieck
|
|
|
Poster
|
Wed 7:30
|
The Need for Speed: Pruning Transformers with One Recipe
Samir Khaki · Konstantinos Plataniotis
|
|
|
Poster
|
Tue 7:30
|
Skip-Attention: Improving Vision Transformers by Paying Less Attention
Shashank Venkataramanan · Amir Ghodrati · Yuki Asano · Fatih Porikli · Amirhossein Habibian
|
|
|
Workshop
|
|
Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
David Hoffmann · Simon Schrodi · Jelena Bratulić · Nadine Behrmann · Volker Fischer · Thomas Brox
|
|
|
Poster
|
Fri 1:45
|
Knowledge Distillation Based on Transformed Teacher Matching
Kaixiang Zheng · EN-HUI YANG
|
|
|
Workshop
|
|
Parallel Time-Sensor Attention for Electronic Health Record Classification
Rachael DeVries · Marie Lisandra Zepeda Mendoza · Ole Winther
|
|
|
Workshop
|
|
Counting on Algorithmic Capacity: The Interplay between Mixing and Memorization in Toy Models of Transformers
Freya Behrens · Luca Biggio · Lenka Zdeborova
|
|
|
Workshop
|
|
Perplexed by Perplexity: Perplexity-Based Pruning with Small Reference Models
Zachary Ankner · Cody Blakeney · Kartik Sreenivasan · Max M Marion · Matthew Leavitt · Mansheej Paul
|
|
|
Workshop
|
|
Scaling Transformers for Skillful and Reliable Medium-range Weather Forecasting
Tung Nguyen · Rohan Shah · Hritik Bansal · Troy Arcomano · Sandeep Madireddy · Romit Maulik · Veerabhadra Kotamarthi · Ian Foster · Aditya Grover
|
|
|
Workshop
|
Sat 1:25
|
Energy Minimizing-based token merging for accelerating Transformers
Duy Nguyen
|
|
|
Workshop
|
|
On the Representation Gap Between Modern RNNs and Transformers: The Curse of Memory Efficiency and the Fix of In-Context Retrieval
Kaiyue Wen · Xingyu Dang · Kaifeng Lyu
|
|
