Add AR RT and OT schemes to Crash FIGConvNet

[Alexey-Kamenev]

PhysicsNeMo Pull Request

Description

1. Added AR RT and OT schemes to Crash FIGConvNet
2. Updated FIGConvUNet model to make scalar output optional (this also fixed "unused parameters" error in DDP).
3. Added tests.

Checklist

• I am familiar with the Contributing Guidelines.
• New or existing tests cover these changes.
• The documentation is up to date with these changes.
• The CHANGELOG.md is up to date with these changes.
• An issue is linked to this pull request.

Dependencies

Review Process

All PRs are reviewed by the PhysicsNeMo team before merging.

Depending on which files are changed, GitHub may automatically assign a maintainer for review.

We are also testing AI-based code review tools (e.g., Greptile), which may add automated comments with a confidence score.
This score reflects the AI’s assessment of merge readiness and is not a qualitative judgment of your work, nor is
it an indication that the PR will be accepted / rejected.

AI-generated feedback should be reviewed critically for usefulness.
You are not required to respond to every AI comment, but they are intended to help both authors and reviewers.
Please react to Greptile comments with 👍 or 👎 to provide feedback on their accuracy.

[greptile-apps]

Greptile Summary

• Added three rollout schemes (AR RT, OT, TC) to FIGConvNet for crash simulation, mirroring existing Transolver and MeshGraphNet implementations
• Made scalar output optional in FIGConvUNet via use_scalar_output parameter, fixing DDP unused parameters error when scalar output is not needed

Important Files Changed

Filename	Overview
physicsnemo/models/figconvnet/figconvunet.py	Made scalar output optional by adding use_scalar_output parameter and conditionally initializing pooling/MLP layers, fixing DDP unused parameters error
examples/structural_mechanics/crash/rollout.py	Added three FIGConvUNet rollout schemes: time-conditional, one-step with teacher forcing, and autoregressive training, following existing patterns for Transolver and MeshGraphNet

[greptile-apps]

_{7 files reviewed, no comments}

_{Edit Code Review Agent Settings | Greptile
React with 👍 or 👎 to share your feedback on this new summary format}

[Alexey-Kamenev]

/blossom-ci

[Alexey-Kamenev]

/blossom-ci

[mnabian]

LGTM!