-
Hey Alex and others,
First of all thank you for your generous work in the field and for spreading the ideas with open source code for the rest of us!
I want to experiment with GFlowNets and poten…
-
We need to re-implement this paper as part of the torchgfn library: https://github.com/GFNOrg/gfn-lm-tuning
In particular many quality of life improvements would be welcome, such as being able to i…
-
When using a conditional gflownet, we need the LogZ estimate (in algorithms such as TB) to be conditional, i.e., predicted from the state.
This means the `logz` parameter must not be constrained to…
-
Does the seh_chembl.csv file contain the results from the GFlowNet model output? I am just checking if I am interpreting the CSV correctly.
-
Hello,
First thank you for this amazing work. I'm starting to work on rna sequence design and GFlowNet is definitely an interesting direction.
I have question for the `RolloutWorker` in `run_amp…
-
Hey @alexhernandezgarcia and others,
As I mentioned in #330 , I want to use Continuous GFNs to estimate the distribution of a 3D dataset for my thesis.
I thought a nice starting point would be [Mode…
-
Thanks for the lovely work! Are there any example scripts for generating conformational ensembles for proteins similar to what is done in the paper [Towards equilibrium molecular conformation generati…
-
I found that `GFNModule` [(here)](https://github.com/GFNOrg/torchgfn/blob/13c059a2d01a6acb5b6fc89fe1ee4e76ad2d4d4d/src/gfn/modules.py) is a parent of `*Estimator` sub-classes. Then, why not naming it …
-
-
**Observation:**
Currently there're no documented conventions on how different methods in different modules (environments, gflownet agent, policies, proxies) interact with each other and it makes it …