Multimodal Large Language Models (MLLMs) have made substantial progress in egocentric video understanding, but their ability to reason cooperatively from multiple embodied viewpoints remains largely unexplored. We study this problem through multi-robot cooperative dynamic spatial reasoning, where a model must answer spatial, temporal, visibility, and coordination questions by integrating synchronized egocentric videos from a team of moving robots. To support this setting, we introduce CoopSR, the first benchmark for this task, together with EgoTeam, a multi-robot egocentric QA dataset. EgoTeam contains 114,227 QA pairs spanning 19 question types, four difficulty tiers, and three team sizes in Habitat and iGibson, along with a real-world test set of around 2,326 QAs collected using two quadruped robots. We further propose SP-CoR (Spectral and Physics-Informed Cooperative Reasoner), an MLLM framework for fine-grained cooperative spatial reasoning. SP-CoR combines dynamics-aware multi-robot frame sampling, spectral- and physics-guided view fusion, and physics-aligned prompt distillation, enabling the model to benefit from privileged robot-pose supervision during training while requiring only egocentric videos at test time. Across 22 MLLM baselines, SP-CoR consistently improves cooperative reasoning, outperforming the strongest fine-tuned baseline by +3.87% on Habitat and +7.12% on iGibson. It also shows stronger generalization to unseen team sizes and real-world robot tests. Code can be found at https://github.com/KPeng9510/seeing-together.git.

A new series on learning AI, from the ground up

I’ve been experimenting with different approaches to running code in a sandbox for several years now, but my latest attempt feels like it might finally have all of the characteristics …

AI as a centralizing technology

Compare cost of living across 1,003 cities in 174 countries. Rent, food, transport, utilities, and salaries — normalized to USD and refreshed regularly.

Fast cross-ecosystem dependency license compatibility checker + Claude Code review skill - shcherbak-ai/licenseal

Support CleanTechnica's work through a Substack subscription or on Stripe. Donut Lab’s latest video reveals a novel manufacturing method. Speculation has swirled around the methods and sources of Donut Lab’s batteries since their introduction. We now have word from them supporting some of the sleuthing that has revealed a different ... [continued]

I do all my work in the terminal, so it has to be quick. How my zsh starts in 30 milliseconds without a framework, and how to measure where your own shell spends its time.

I do all my work in the terminal, so it has to be quick. How my zsh starts in 30 milliseconds without a framework, and how to measure where your own shell spends its time.

⚫ Reconstructed tables ⚫ Census ⚫ Online works ⚫ Computing aids ⚫ Pi ⚫ Sustainable digitization ⚫ Nancy The aim of the LOCOMAT project is to make available a number of interesting and/or important historical tables, and to facilitate the study of the original tables by historians of mathematics. An overview of the motivations of the project appears in Denis Roegel, "The LOCOMAT Project: Recomputing Mathematical and Astronomical Tables", IEEE Annals of the History of Computing, April-June 2012, pages 74-79. Slides of an overview of the project can be found here (in French). This page is located at http://locomat.loria.fr/ GDML (Global Digital Mathematics Library)

Stop manual data entry. Extract structured data from global IDs, VINs, HINs, Invoices and Receipts with 98.5% accuracy. No credit card required to start.

Scott Stanfield forwarded me a link to Roger Sessions’ A Better Path to Enterprise Architecture yesterday. Even though it’s got the snake-oil word “Enterprise” in the title, the article is surprisingly good. I particularly liked the unusual analogy Roger chose to illustrate the difference between iterative and recursive approaches