Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision

Computer Science > Robotics arXiv:2609.20820v1 (cs) [Submitted on 17 Sep 2026] Title:Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision Authors:Nitish Dashora, Douglas Chen, Idan Shenfeld, John Marangola, Pulkit Agrawal, Max Simchowitz View a PDF of the paper titled Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision, by Nitish Dashora and 5 other authors View PDF HTML (experimental) Abstract:Complex robotic manipulation tasks frequently require a long-term memory of past events and actions. As conditioning on full histories renders policies prone to spurious correlations and degrades performance, many approaches to policy memory involve compressing historical information through expensive VLM queries in-the-loop to process only task-salient information. In this paper, we propose an alternative approach in which computationally intensive VLM queries are made during train-time to learn a lightweight latent memory that can be efficiently queried at deployment time. Our representation, which we call the \textbf{workspace token}, is trained by (1) using a VLM to identify current and historical information necessary for completing a task, then (2) distilling these into the workspace token using a set-reconstruction decoder loss. In both simulation and hardware, we show that the workspace token can be used as a drop-in replacement for observations during deployment, enabling policies to solve memory-intensive tasks without the need for VLM reasoning in-the-loop. Interestingly, we found that workspace tokens are not only more lightweight but also lead to better policy performance. Comments: Subjects: Robotics (cs.RO); Artificial Intelligence (cs.AI) Cite as: arXiv:2609.20820 [cs.RO] (or arXiv:2609.20820v1 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2609.20820 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Nitish Dashora [view email] [v1] Thu, 17 Sep 2026 17:59:53 UTC (12,984 KB) Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)