BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//hackathonmaxxing//EN
CALSCALE:GREGORIAN
X-WR-CALNAME:Hackathons in Berlin
BEGIN:VEVENT
UID:luma:evt-Lf3Mx0lWC4lwWox@hackathonmaxxing
DTSTAMP:20261122T174113Z
DTSTART:20261130T173000Z
DTEND:20261130T190000Z
SUMMARY:BRISA Reading Group 08 - VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model
URL:https://lu.ma/1lk2u1qn?utm_source=hackathonmaxxing&utm_medium=referral&utm_campaign=berlin
LOCATION:Merantix AI Campus\, Berlin\, Germany
DESCRIPTION:This Monday we are looking at VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model (Guo\, Lee\, Shi\, Chen\, Liang & Finn\, 2026) from Stanford and Tsinghua\, presented at ICML 2026.\n\nTwo weeks ago\, Long-WAM built prediction into the policy itself. VLAW keeps policy and world model separate and asks whether each can make the other better.\n\nImproving a robot policy through practice means running it again and again on real hardware\, which is slow and expensive. A learned world model could stand in as the simulator. However\, today’s world models are trained mostly on successful demonstrations: they are too optimistic and they miss the small physical details that decide whether a contact-rich task works.\n\nVLAW closes the loop\, by rolling out the policy (π0.5) on a real Franka arm (failures included). Those rollouts finetune the world model. The policy then practises inside the improved world model at scale\, a vision-language model judges which imagined attempts succeeded and the policy is finetuned on the successful real and synthetic ones.\n\nAcross contact-rich tasks like scooping\, erasing marks and stacking\, this improves success by 39.2 percentage points over the base policy\, with 11.6 of those coming from the synthetic rollouts.\n\nAs always: No preparation needed.\n\nCome with questions\, disagreements\, or your own take on how much a robot can learn from its own imagination.\n\n🎟️ There are only a limited number of spots\, so we can keep the session personal and interactive. Please register early and only attend if you’ve received a ticket.\n\n📍 Hosted at the Merantix AI Campus on November 30th. Doors open 18:30\, we start at 18:45.\n\n👋 New here? Join the community group - everything else gets announced there first. https://lu.ma/1lk2u1qn?utm_source=hackathonmaxxing&utm_medium=referral&utm_campaign=berlin
END:VEVENT
END:VCALENDAR
