|
Workshop
|
|
A theoretical study of the (L0,L1)-smoothness condition in deep learning
Y Cooper
|
|
|
Poster
|
Fri 16:30
|
Nuclear Norm Regularization for Deep Learning
Christopher Scarvelis · Justin Solomon
|
|
|
Poster
|
Thu 16:30
|
Approximation Rate of the Transformer Architecture for Sequence Modeling
Haotian Jiang · Qianxiao Li
|
|
|
Poster
|
Thu 11:00
|
Improving Adaptivity via Over-Parameterization in Sequence Models
Yicheng Li · Qian Lin
|
|
|
Poster
|
Wed 16:30
|
Non-asymptotic Convergence of Training Transformers for Next-token Prediction
Ruiquan Huang · Yingbin Liang · Jing Yang
|
|
|
Poster
|
Fri 16:30
|
Deep Learning for Computing Convergence Rates of Markov Chains
Yanlin Qu · Jose Blanchet · Peter W Glynn
|
|
|
Poster
|
Wed 11:00
|
Optimal and Approximate Adaptive Stochastic Quantization
Ran Ben-Basat · Yaniv Ben-Itzhak · Michael Mitzenmacher · Shay Vargaftik
|
|
|
Poster
|
Thu 16:30
|
Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformation
Shiyu Xia · Yuankun Zu · Xu Yang · Xin Geng
|
|
|
Poster
|
Thu 11:00
|
Neural Concept Binder
Wolfgang Stammer · Antonia Wüst · David Steinmann · Kristian Kersting
|
|
|
Poster
|
Thu 11:00
|
AdanCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer
Yitao Xu · Tong Zhang · Sabine Süsstrunk
|
|
|
Poster
|
Wed 11:00
|
SAM-Guided Masked Token Prediction for 3D Scene Understanding
Zhimin Chen · Liang Yang · Yingwei Li · Longlong Jing · Bing Li
|
|
|
Poster
|
Thu 16:30
|
Selective Attention: Enhancing Transformer through Principled Context Control
Xuechen Zhang · Xiangyu Chang · Mingchen Li · Amit Roy-Chowdhury · Jiasi Chen · Samet Oymak
|
|
