-
[Visualizing and Understanding Recurrent Networks](https://arxiv.org/abs/1506.02078)
Recurrent Neural Networks (RNNs), and specifically a variant with Long Short-Term Memory (LSTM), are enjoying rene…
-
This [post](https://www.lesswrong.com/posts/mkbGjzxD8d8XqKHzA/the-singular-value-decompositions-of-transformer-weight
) is awesome. I think the value from using this method comes from both understandi…
-
This is looking good. For this project, I would try to focus on more interpretable models. If you are going to use something like boosting trees, try to either figure out a good way to interpret them …
-
First of all, Thank you for this wonderful package.
I would like to try fitting a flexible parametric model relaxing the PH assumption (this was requested by the physician for clinical reasons relate…
-
As for the question, I am very curious about the vision encoder with diffusion models, and how does this align with the semantic world.
-
Implement 'Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models'
Basically allows fine grained image tweaks using 'sliders'
- Paper: https://arxiv.org/abs/2311.12092
- > We …
-
[Why should I trust you?: Explaining the predictions of any classifier](https://arxiv.org/abs/1602.04938)
Despite widespread adoption, machine learning models re- main mostly black boxes. Understandi…
-
🔍 **Deep Dive: "ReAct: Reasoning and Acting with Large Language Models"**
📝 **Summary:**
The authors introduce "ReAct", a method that synergizes reasoning and acting in large language models (LL…
-
# Captum LIME API Design
## Background
LIME is an algorithm which interprets a black-box model by training an interpretable model, such as a linear model, based on local perturbations around a p…
-
Hello Dr. Phillippo,
Thanks again for your help with addressing issue #43 (where aux_regression terms were not always included in the predict function). I'd like to report a similar issue with rela…