Transformer

2020-08 The Chess Transformer: Mastering Play using Generative Language Models	2020/08/11 14:23	Hyunsoo Park
2020-08 Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention	2020/09/03 08:50	Hyunsoo Park
2020-10 Beyond English-Centric Multilingual Machine Translation	2021/07/18 13:31	Hyunsoo Park
2020-12 The Monte Carlo Transformer: a stochastic self-attention model for sequence prediction	2020/07/22 14:09	Hyunsoo Park
2021-01 Addressing Some Limitations of Transformers with Feedback Memory	2021/07/17 13:45	Hyunsoo Park
2021-03 Pay Attention to MLPs	2021/07/27 01:33	Hyunsoo Park
2021-06 Decision Transformer: Reinforcement Learning via Sequence Modeling	2021/07/17 15:51	Hyunsoo Park
2021-06 Reinforcement Learning as One Big Sequence Modeling Problem	2021/07/17 15:41	Hyunsoo Park
2021-07 Perceiver IO: A General Architecture for Structured Inputs & Outputs	2021/08/04 01:07	Hyunsoo Park
2021-12 Differentiable Spatial Planning using Transformers	2021/12/07 16:27	Hyunsoo Park
2023-10 AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents	2024/11/19 05:53	Hyunsoo Park
A Spatio-temporal Transformer for 3D Human Motion Prediction	2020/08/02 18:56	Hyunsoo Park
Attention Is All You Need	2020/07/23 14:51	Hyunsoo Park
Big Bird: Transformers for Longer Sequences	2020/08/05 23:13	Hyunsoo Park
Compressive Transformer	2020/02/11 17:24	Hyunsoo Park
CrossTransformers: spatially-aware few-shot transfer	2020/07/25 03:58	Hyunsoo Park
CTRL: A Conditional Transformer Language Model for Controllable Generation	2020/07/30 17:59	Hyunsoo Park
SliceOut: Training Transformers and CNNs faster while using less memory	2020/07/24 18:14	Hyunsoo Park