firstbacksecondback
166 Results
Poster
|
Transformer-Patcher: One Mistake Worth One Neuron Zeyu Huang · Yikang Shen · Xiaofeng Zhang · Jie Zhou · Wenge Rong · Zhang Xiong |
||
Poster
|
Transformer-based model for symbolic regression via joint supervised learning Wenqiang Li · Weijun Li · Linjun Sun · Min Wu · Lina Yu · Jingyi Liu · Yanjie Li · Songsong Tian |
||
Workshop
|
Thu 4:00 |
TabRet: Pre-training Transformer-based Tabular Models for Unseen Columns Soma Onishi · Kenta Oono · Kohei Hayashi |
|
Poster
|
On amortizing convex conjugates for optimal transport Brandon Amos |
||
Poster
|
Tue 2:30 |
Transformer-based World Models Are Happy With 100k Interactions Jan Robine · Marc Höftmann · Tobias Uelwer · Stefan Harmeling |
|
Poster
|
On the Data-Efficiency with Contrastive Image Transformation in Reinforcement Learning Sicong Liu · Xi Zhang · Yushuo Li · Yifan Zhang · Jian Cheng |
||
Workshop
|
Fri 5:50 |
AnomalyBERT: Self-Supervised Transformer for Time Series Anomaly Detection using Data Degradation Scheme Yungi Jeong · Eunseok Yang · Jung Hyun Ryu · Imseong Park · Myungjoo Kang |
|
Poster
|
Mon 2:30 |
CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers Wenyi Hong · Ming Ding · Wendi Zheng · Xinghan Liu · Jie Tang |
|
Poster
|
Tue 2:30 |
Treeformer: Dense Gradient Trees for Efficient Attention Computation Lovish Madaan · Srinadh Bhojanapalli · Himanshu Jain · Prateek Jain |
|
Poster
|
Wed 7:30 |
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation Bobby He · James Martens · Guodong Zhang · Aleksandar Botev · Andrew Brock · Samuel L Smith · Yee Whye Teh |
|
Poster
|
Tue 7:30 |
The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers Zonglin Li · Chong You · Srinadh Bhojanapalli · Daliang Li · Ankit Singh Rawat · Sashank Reddi · Ke Ye · Felix Chern · Felix Yu · Ruiqi Guo · Sanjiv Kumar |
|
Poster
|
Wed 2:30 |
Clifford Neural Layers for PDE Modeling Johannes Brandstetter · Rianne van den Berg · Max Welling · Jayesh Gupta |