-
Hi,
I hope these new papers may be of interest to you.
PAPERS:
- LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs? @KDD24
- url: https://arxiv.org/abs/2310.…
-
-
## 🐛 Bug
After wrapping up an `nn.Module` layer into `torch.nn.utlis_spectral_norm`, it fails to be copied after the first forward pass.
## To Reproduce
```python
import torch
import copy
…
-
There is already a dataset class that contains one single valued measurements like reflectivity or transmission. Of course we would also like to store and have a simple and unified way to deal with da…
-
Your spectral normalization normalizes the spectral norm of the weight matrix W so that it satisfies the Lipschitz constraint = 1. So we consider whether to combine the wasserstein gan with spectral n…
-
I'm starting to look at how to do testing for subgrids and/or source density splitting. As a first step, I want to check the SED grids, which are created in `create_physicsmodel.py`. But it looks li…
-
Possibly could be done by artificially shifting the spectra from different instruments to non-overlapping wavelengths (w/ appropriate scalings) and constraining the common features for the fitting. T…
-
Hi Steffen,
Thank you for your AAAI paper and this repo.
I wonder if you could provide the pre-trained models for easier reproduction of your results in the paper.
Best,
Shengwei
-
I am following the demo ["Performing Inversions of Bolometer Measurements Using the Voxel Framework"](https://www.cherab.info/demonstrations/bolometry/inversion_with_voxels.html). I have the voxels an…
-
在执行训练命令时报错了。
命令：!python3.8 finetune_speaker_v2.py -m "./OUTPUT_MODEL" --max_epochs 1000 --drop_speaker_embed True
报错日志：
`INFO:OUTPUT_MODEL:{'train': {'log_interval': 10, 'eval_interval': 100, 'se…