firstbacksecondback
15 Results
|
Workshop
|
TabFlex: Scaling Tabular Learning to Millions with Linear Attention Yuchen Zeng · Wonjun Kang · Andreas Mueller |
||
|
Workshop
|
Linear Attention Sequence Parallelism Weigao Sun · Zhen Qin · Dong Li · Xuyang Shen · Yu Qiao · Yiran Zhong |
||
|
Workshop
|
Sat 13:00 |
Panel: On Linear Representations and Pretraining Data Frequency in Language Models When Attention Sink Emerges in Language Models: An Empirical View Common Functional Decompositions Can Mis-attribute Differences in Outcomes Between Populations U-shape |
|
|
Poster
|
Fri 16:30 |
Parallelizing Linear Transformers with the Delta Rule over Sequence Length Songlin Yang · Bailin Wang · Yu Zhang · Yikang Shen · Yoon Kim |
|
|
Poster
|
Wed 11:00 |
Linear Transformers are Versatile In-Context Learners Max Vladymyrov · Johannes von Oswald · Mark Sandler · Rong Ge |
|
|
Poster
|
Fri 16:30 |
How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression Xingwu Chen · Lei Zhao · Difan Zou |
|
|
Poster
|
Wed 16:30 |
QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion Yixing Xu · Chao Li · Dong Li · Xiao Sheng · Fan Jiang · Lu Tian · Emad Barsoum |
|
|
Poster
|
Thu 16:30 |
Bridging the Divide: Reconsidering Softmax and Linear Attention Dongchen Han · Yifan Pu · Zhuofan Xia · Yizeng Han · Xuran Pan · Xiu Li · Jiwen Lu · Shiji Song · Gao Huang |
|
|
Poster
|
Wed 16:30 |
Demystify Mamba in Vision: A Linear Attention Perspective Dongchen Han · Ziyi Wang · Zhuofan Xia · Yizeng Han · Yifan Pu · Chunjiang Ge · Jun Song · Shiji Song · Bo Zheng · Gao Huang |
|
|
Workshop
|
In-Context Learning by Linear Attention: Exact Asymptotics and Experiments Yue Lu · Mary Letey · Jacob Zavatone-Veth · Anindita Maiti · Cengiz Pehlevan |
||
|
Workshop
|
Sat 15:00 |
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues Riccardo Grazzi · Julien Siems · Jörg Franke · Arber Zela · Frank Hutter · Massimiliano Pontil |
|
|
Workshop
|
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues Riccardo Grazzi · Julien Siems · Jörg Franke · Arber Zela · Frank Hutter · Massimiliano Pontil |