firstbacksecondback
297 Results
|
Poster
|
Wed 8:45 |
Training Transformers with 4-bit Integers Haocheng Xi · ChangHao Li · Jianfei Chen · Jun Zhu |
|
|
Poster
|
Tue 15:15 |
Geometric Transformer with Interatomic Positional Encoding Yusong Wang · Shaoning Li · Tong Wang · Bin Shao · Nanning Zheng · Tie-Yan Liu |
|
|
Poster
|
Wed 8:45 |
State Sequences Prediction via Fourier Transform for Representation Learning Mingxuan Ye · Yufei Kuang · Jie Wang · Yang Rui · Wengang Zhou · Houqiang Li · Feng Wu |
|
|
Poster
|
Tue 8:45 |
Facing Off World Model Backbones: RNNs, Transformers, and S4 Fei Deng · Junyeong Park · Sungjin Ahn |
|
|
Poster
|
Wed 8:45 |
The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit Lorenzo Noci · Chuning Li · Mufan Li · Bobby He · Thomas Hofmann · Chris Maddison · Dan Roy |
|
|
Poster
|
Wed 15:00 |
SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations Qitian Wu · Wentao Zhao · Chenxiao Yang · Hengrui Zhang · Fan Nie · Haitian Jiang · Yatao Bian · Junchi Yan |
|
|
Poster
|
Wed 8:45 |
Causal Interpretation of Self-Attention in Pre-Trained Transformers Raanan Rohekar · Yaniv Gurwicz · Shami Nisimov |
|
|
Poster
|
Thu 8:45 |
Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction Zechuan Zhang · Li Sun · Zongxin Yang · Ling Chen · Yi Yang |
|
|
Poster
|
Thu 15:00 |
Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing Yelysei Bondarenko · Markus Nagel · Tijmen Blankevoort |
|
|
Poster
|
Wed 8:45 |
NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning Yun Yi · Haokui Zhang · Rong Xiao · Nannan Wang · Xiaoyu Wang |
|
|
Poster
|
Wed 8:45 |
Learning Transformer Programs Dan Friedman · Alexander Wettig · Danqi Chen |
|
|
Poster
|
Thu 8:45 |
Focused Transformer: Contrastive Training for Context Scaling Szymon Tworkowski · Konrad Staniszewski · Mikołaj Pacek · Yuhuai Wu · Henryk Michalewski · Piotr Miłoś |