This checkpoint adds an Action-Aware Adaptive Memory (AAM) module on top of the HAMLET window architecture for GR00T N1.6, trained on RoboMME. The memory module uses a log-spaced 8-frame window [-1024, -512, -256, -128, -64, -32, -16, 0] env-steps; each past observation slot receives a learned per-slot soft gate weight, feeding a 2-layer MemoryTransformer that conditions the DiT flow-matching action head. A second prediction head performs action-conditioned forward prediction as an auxiliary loss. Trainable components: DiT + projector + moment tokens + top-4 LLM layers + gate + prediction head; the remainder of the VLM backbone is frozen.

Eval harness: 10 episodes/task, checkpoint-60000. Vanilla GR00T N1.6 = 10.12 avg, HAMLET baseline = 16.5 avg.

The adaptive gate is strong at selective recall (Permanence ties HAMLET) but weak at temporal integration (Counting).