|
Poster
|
Wed 16:30
|
Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis
Rachel S.Y. Teo · Tan Nguyen
|
|
|
Poster
|
Fri 16:30
|
NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention
Tianyi Zhang · Jonah Yi · Bowen Yao · Zhaozhuo Xu · Anshumali Shrivastava
|
|
|
Affinity Event
|
|
Reducing Reasoning Costs - The Path of Optimization for Chain of Thought via Sparse Attention Mechanism
Libo Wang
|
|
|
Poster
|
Thu 11:00
|
Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching
Fernando Moreno-Pino · Alvaro Arroyo · Harrison Waldon · Xiaowen Dong · Alvaro Cartea
|
|
|
Workshop
|
|
Transformers are Efficient Compilers, Provably
Xiyu Zhai · Runlong Zhou · Liao Zhang · Simon Du
|
|
|
Poster
|
Fri 11:00
|
Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers
Markus Hiller · Krista A. Ehinger · Tom Drummond
|
|
|
Poster
|
Fri 11:00
|
Activating Self-Attention for Multi-Scene Absolute Pose Regression
Miso Lee · Jihwan Kim · Jae-Pil Heo
|
|
|
Poster
|
Thu 16:30
|
On the Role of Attention Masks and LayerNorm in Transformers
Xinyi Wu · Amir Ajorlou · Yifei Wang · Stefanie Jegelka · Ali Jadbabaie
|
|
|
Poster
|
Wed 16:30
|
Graph Convolutions Enrich the Self-Attention in Transformers!
Jeongwhan Choi · Hyowon Wi · Jayoung Kim · Yehjin Shin · Kookjin Lee · Nathaniel Trask · Noseong Park
|
|
|
Poster
|
Wed 11:00
|
Single Image Reflection Separation via Dual-Stream Interactive Transformers
Qiming Hu · Hainuo Wang · Xiaojie Guo
|
|
|
Poster
|
Wed 16:30
|
Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling
Mahdi Karami · Ali Ghodsi
|
|
|
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
|
|
