-
Regardless of whether the UAI submission comes through, I think we should publish the paper on arxiv at some point soon. For this I think it's extremely important to do a bit of PR. I have been thinki…
-
### 🚀 The feature, motivation and pitch
Hello,
First and foremost, I apologize for potentially misplacing this issue in the wrong section.
When working with the negative sampling part and the neces…
-
Dear AlphaFold Team,
Firstly, thank you for your groundbreaking work with AlphaFold 3. The advancements you've made in biological structure prediction are truly inspiring.
I am writing to introd…
-
Hello, I noticed that you used the `mask_predictions` from the `mask_decoder` as the `masks` prompt for the `prompt_encoder`. I tried to use a binary image (a prediction result generated by another se…
-
A long-standing problem that I want to solve with the next release is the handling of the weights. The problem is the following:
Depending on the family, weights are either included in the simulati…
-
colab 训练提示 “libcuda.so cannot found”
-
You do not need to put in anything here :)
Just open the issue by clicing the green "Submit new issue" and within 10-15s a message instructing you do upload your files should appear!
-
Hi, thank you for sharing this amazing project with the rest of the world. I have the honour to use maia for my experimentation, but I have some problems and you may be able to help me with.
Proble…
-
When using mice multiple imputation to generate multiple imputed sets and then running a model on each one of them (like elastic-net from the `glmnet` package) and then pooling the estimates to a sing…
-
why are you making the loss negative before taking top_k losses
**vals, _ = tf.nn.top_k(-neg_conf, k=n_neg)**