Published on Sep 2 · Submitted by yincheng on Sep 8 · OpenBMB Abstract SimpleMemVLA achieves long-horizon manipulation by feeding intact timestamped video history directly into a pretrained VLM backbone and using hidden states to inform a flow-matching action head, outperforming dedicated memory modules. Long-horizon manipulation is partially observable: the information needed to choose the next action may appear only in observations from minutes earlier.
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Get in touch with Junpeng
Contact Junpeng, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack