|
Poster
|
Thu 1:45
|
Dynamic Layer Tying for Parameter-Efficient Transformers
Tamir David-Hay · Lior Wolf
|
|
|
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
|
|
|
Workshop
|
|
Rough Transformers for Continuous and Efficient Time-Series Modelling
Fernando Moreno-Pino · Alvaro Arroyo · Harrison Waldon · Xiaowen Dong · Alvaro Cartea
|
|
|
Poster
|
Tue 1:45
|
ALAM: Averaged Low-Precision Activation for Memory-Efficient Training of Transformer Models
Sunghyeon Woo · SunWoo Lee · Dongsuk Jeon
|
|
|
Poster
|
Fri 7:30
|
Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models
Yili Wang · Kaixiong Zhou · Ninghao Liu · Ying Wang · Xin Wang
|
|
|
Poster
|
Tue 7:30
|
Complete and Efficient Graph Transformers for Crystal Material Property Prediction
Keqiang Yan · Cong Fu · Xiaofeng Qian · Xiaoning Qian · Shuiwang Ji
|
|
|
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
|
|
|
Workshop
|
|
Perplexed by Perplexity: Perplexity-Based Pruning with Small Reference Models
Zachary Ankner · Cody Blakeney · Kartik Sreenivasan · Max M Marion · Matthew Leavitt · Mansheej Paul
|
|
