-
# URL
- https://arxiv.org/abs/2411.05663
# Authors
- Xiwen Wei
- Guihong Li
- Radu Marculescu
# Abstract
- Catastrophic forgetting is a significant challenge in online continual learning (OCL)…
-
Reason: to support continual learning with LLM, such as:
* Use historical interaction log to improve the performance of an agent with the accumulation of interaction sessions.
* Summarize data that …
-
I was wondering if it would be possible for HiClass to incorporate **Online/Continual Learning** to process streams of data. Something like what is implemented in a library like "avalanche" https://g…
-
Cycle Consistency + Decision Transformer
Like world model, we learn a forward and back dynamic model. Then we use these DMs to constraint decision transformer training using cycle consistency const…
-
-
-
First, thank you for your great effort in your survey and code implementation : )
I am using it well for my research and I have a question. I tried to reproduce the result in your paper.
In Tabl…
-
Simple example showing continual learning with the Laplace approximation on toy data.
-
Here some key Aptos could focus on to help onboard new users:
- Simplify the onboarding experience. Make it very easy to set up a wallet and receive small amounts of Aptos to try it out.
- Integrat…
-
We need to support some model combination:
There is the default OpenNMT one, but it does not work, see https://github.com/OpenNMT/OpenNMT-py/issues/1252