Learnt quite about latency and action chunk regarding inference with some robotics VLA models . Making multi-agent pipelines is full of some intricancies, but gosh this is fun!!!!! https://t.co/8RzggSjZFN
🔥¡Comienza la carrera para @SPIEL_Messe 2026!🔥 Tras el éxito de #Orloj seguimos apostando fuerte, esta vez con #Nijar y #ASHES. Es un momento clave y os necesitamos. ¡Pulgarcito y must have! Gracias😍
👇👇
https://t.co/lzSr1SMZ0b
Introducing ACT-2 Preview
The first robotics model to unify broad generalization with high reliability. A single fine-tuning example can teach Memo a new behavior that generalizes.
Zero shot, real unseen homes, 99% success rate.
One of the best things about OpenSource is when you see the community using stuff in amazing ways you would have never thought about! + super kind person and interaction. Grande! https://t.co/zB1pGbMElC
Good week learning about multiple envs config for a multiagent Franka experiment . OpenVLA+gemma4. Long life to setup bash scripts!!! Have a look at the tutorial. https://t.co/vVGWJoT2Am . Happy to see you around Github!! #opensource#robotics
🎉 ¡Anunciamos nuestra segunda keynote speaker para #PyConES2026: Mia Bajić! 🐍
Ingeniera de software, Vicepresidenta de la EuroPython Society y presentadora de Behind the Commit. ¡Más información en la web!
🔗 https://t.co/SDAfoudOVu
#Keynote#PyConES#Python
Es oficial, vuelvo al Open Source! Esta vez como maintainer. Vertigo , pero tb sentirse como nunca! https://t.co/yT0HVvpIhr Ademas lo cuento en la @PyConES en Barna !!!
Introducing ABC: open data, training, and infrastructure for robotics.
We release the largest teleop dataset to date, and extensively investigate design decisions, pretraining, and post-training techniques.
@arthurallshire@Cinnabar233@adamrasb@redstone_hong@davidrmcall
Together with @schmidtsciences, @GoogleDeepMind, @ARIA_research, and supported by @Googleorg, we’re announcing a new $10m fund to support the foundational scientific research needed to understand, evaluate, and control risks emerging from large-scale ecosystems of interacting AI agents, deployed by multiple actors.
If you’re a researcher or developer working on tools for scaling public deliberation, collective decision-making, and AI-facilitated cooperation, apply for our workshop with @foresightinst, held in Seoul right before @icmlconf on Sunday 5 July 2026.
Atrás quedó nuestra etapa como artesanos del código. El código es solo un subproducto, el objetivo real es resolver problemas de negocio. Ya no eres programador. Eres solucionador de problemas tecnológicos que utiliza las mejores herramientas disponib ... Subscribo cada palabra