Spa-Bench/spa-bench-model-molmoact2-step-076596

MolmoAct2 — Spa-Bench Step 76,596

This checkpoint is released as an anonymous supplementary artifact for a paper under double-blind review. It was evaluated on a physical SO-101 robot in Spa-Bench.

Model details

Field	Value
Checkpoint	End of epoch 12; step 76,596
Inputs	Middle RGB, wrist RGB, six joint positions, and a text instruction
Outputs	Six absolute joint-position targets
Action horizon	30
Adaptation	VLM and continuous-action expert updated; token embeddings frozen
Optimizer	AdamW; zero weight decay; component-specific learning rates

Training-data documentation: spa-bench-training-teleoperation-1200.

Physical evaluation

87/120 familiar trials, 156/300 withheld-composition trials, 73/120 matched withheld trials, and 107/120 matched direct-manipulation controls. These are physical rollout results, not simulation metrics.

Rollouts: spa-bench-eval-rollouts-molmoact2-full.

Limitations and safety

Results apply to this checkpoint, SO-101 embodiment, workspace, cameras, objects, and physical protocol. Robot policies can move hardware unexpectedly. Use conservative limits, an accessible emergency stop, a clear workspace, and direct supervision. Do not deploy unattended or in safety-critical settings.

Double-blind release note

Author, institution, source-repository, and archival citation details are intentionally omitted during review. They will be restored in the archival release.