Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
|
Hi @rgeirhos, we have updated the results for Cosmos3 V2V (multiframe) Super and Nano models, could you please review/ merge them? |
|
cc. @jwgu |
|
@tuliti does this look good on your end? |
|
Thanks @arslananvidia! Happy to merge if @tuliti indicates LGTM. |
|
Hi @arslananvidia, appreciate the submissions! We decribe the process in the Readme Section Physics-IQ Verified Workflow If you need any further help, we are happy to help. |
|
Hi @tuliti , could you please let me know how I can obtain the s3 credentials to upload the videos? My email address is arslana@nvidia.com. |
|
@tuliti @rgeirhos I have Uploaded both Nano and Super runs and cards to the public Hugging Face dataset (https://huggingface.co/datasets/arslannvidia/cosmos3-physicsiq-evidence-v2v/tree/main) |
|
Hi @arslananvidia, @rgeirhos, the PR can be merged from our side now. |
|
@arslananvidia |
|
@sten2lu, thank you for the review. I have removed the other files, leaving only the README. Could you please merge the PR into the main branch? |
|
Thanks @arslananvidia for the PR, and congrats on the results - it's now merged. Also, thanks @sten2lu for confirming that everything looks good on your end. |


V2V (multiframe) results for Cosmos3 Super and Cosmos3 Nano.
Cosmos-3 Super: 50.8 ± 2.2
Cosmos-3 Nano: 43.0 ± 2.0