Robotics & World Models Reading Club 09: CVPR Warm-up & Founders Spotlight — DeltaWorld + VisuoTactile Dexterous Hands | San Francisco 0523

​Robotics & World Models Reading Club 09: CVPR Warm-up & Founders Spotlight — DeltaWorld + VisuoTactile Dexterous Hands | San Francisco 0523

​A high-signal reading group for AI researchers & builders pushing the frontiers of robotic world models, WAMs, and embodied intelligence. In our previous sessions, we brought together researchers and engineers from Boston Dynamics, Google, NVIDIA, Stanford, UC Berkeley, CMU, Dyna, ByteDance, Tesla, Generalist, Rhoda AI, and leading Bay Area robotics startups.

​Hosted by Junfan Zhu & Aurora Feng.

​Supported by Neural Motion, a universal cross-embodiment data representation layer for embodied AI.

​​Reading Club 09's Core Theme

​Keynote 1 by Tommie Kerssies (Amazon Frontier AI & Robotics)

​A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens

​Anticipating diverse future states is a central challenge in video world modeling. Discriminative world models produce a deterministic prediction that implicitly averages over possible futures, while existing generative world models remain computationally expensive. Recent work demonstrates that predicting the future in the feature space of a vision foundation model (VFM), rather than a latent space optimized for pixel reconstruction, requires significantly fewer world model parameters. However, most such approaches remain discriminative. In this work, we introduce DeltaTok, a tokenizer that encodes the VFM feature difference between consecutive frames into a single continuous "delta" token, and DeltaWorld, a generative world model operating on these tokens to efficiently generate diverse plausible futures. Delta tokens reduce video from a three-dimensional spatio-temporal representation to a one-dimensional temporal sequence, for example yielding a 1,024x token reduction with 512x512 frames. This compact representation enables tractable multi-hypothesis training, where many futures are generated in parallel and only the best is supervised. At inference, this leads to diverse predictions in a single forward pass. Experiments on dense forecasting tasks demonstrate that DeltaWorld forecasts futures that more closely align with real-world outcomes, while having over 35x fewer parameters and using 2,000x fewer FLOPs than existing generative world models.

​Keynote 2 by Arjun Subramaniam (Factory Intelligence)

​ManiFeel

​​​​Pre-Readings

​Keynote 1 by Tommie Kerssies (Amazon Frontier AI & Robotics)

​A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens

​TiTok: https://arxiv.org/abs/2406.07550
DINOv3: https://arxiv.org/pdf/2508.10104
Back to the Features: DINO as a Foundation for Video World Models: https://arxiv.org/abs/2507.19468

​Keynote 2 by by Arjun Subramaniam (Factory Intelligence)

​ManiFeel

​​Location

​San Francisco (Downtown)

​​​​​Date & Time

​Saturday, May 23, 2026 | 2:00 PM – 5:00 PM

​​​​​​Join Discord Community

​https://discord.gg/WH7DrTHRXK

​​​​​Follow Saturday Robotics on X

​https://x.com/saturdayrobotic

​​​​​Agenda

​2:00 PM – 2:30 PM Door Opens & Social

• ​Food 😋, beverages🧋 and UNLIMITED strawberries 🍓 (our official reading club fruits ☺️😄).

​2:30 PM – 3:00 PM Keynote 1 by Tommie Kerssies (Amazon Frontier AI & Robotics), DeltaWorld: Generating Diverse Video Futures with Delta Tokens

​3:00 PM – 3:30 PM Keynote 2 by

​Online access via Zoom: TBD

​YouTube Recording: TBD (We are looking for recording volunteers)

​3:30 PM – 5:00 PM Q&A, ​open-floor roundtable (10–20 min per topic) on spotlight papers or any paper you’d like to highlight. Feel free to share why the paper matters and its technical details.

​​​​Future events

​#cvpr-denver-meetup-0606: Saturday Robotics CVPR & World Models Researchers Meetup—Denver 0606

• ​CVPR Denver Luma: https://luma.com/zamm9g2g

​​Past events

​#reading-club-08-0516: Embodied Human Data as the “Internet of Motion and Behavior”

• ​Session 08 Luma: https://luma.com/qoxioge7

​#reading-club-07-0509: Learning to Dream: World Models, Imagination, Path to Foundation Models for Control

• ​Session 07 Luma: https://luma.com/srhe0vuo

​#reading-club-06-0502: Evolution of Video World Models for Robotics

• ​Session 06 Luma: https://luma.com/sdrd4zwr

• ​Reading Club 06 Review: https://x.com/junfanzhu98/status/2050834699275383008?s=20

​#reading-club-05-0425: World Models for Physical Intelligence: From Predictive Brains to Embodied Robots

• ​Session 05 Luma: https://luma.com/p7zvpyvg

• ​Reading Club 05 Review: https://x.com/junfanzhu98/status/2048315020946317710?s=20

• ​YouTube Recording: https://youtu.be/RVy6oQXNDgc?si=u2VLtCBjfdMvXaf-

​#reading-club-04-0418: Abstractions of the Physical World for Decision-Making

• ​Session 04 Luma: https://luma.com/atv7bm3i

• ​Reading Club 04 Review: https://x.com/junfanzhu98/status/2045770010979905862

• ​YouTube Recording: https://www.youtube.com/@saturdayrobotic

​#reading-club-03-0411: Robotic Policy Adaptation

• ​Session 03 Luma: https://luma.com/561xgirg

• ​Reading Club 03 Review: https://x.com/junfanzhu98/status/2043243484568768519?s=20

• ​YouTube Recording: https://www.youtube.com/@saturdayrobotic

​#reading-club-02-0404: JEPA Zoo

• ​Session 02 Luma: https://luma.com/g3qrrti0

• ​Reading Club 02 Review (liked by Yann LeCun on X): https://x.com/junfanzhu98/status/2040716119259164673?s=20

​#reading-club-01-0328

• ​Session 01 Luma: https://luma.com/8s4w1wu6

• ​Reading Club 01 Review (liked by Yann LeCun on X): https://x.com/junfanzhu98/status/2038153945219305812

​​​​​Logistics

​Spots are limited. Please arrive by 2:00 PM for check-in. Keynote will begin promptly at 2:30 PM.

• ​We currently do not have volunteers available to assist with late check-ins. Given the high volume of inquiries and 100+ attendees (both online and onsite), we kindly ask that you arrive on time to ensure smooth entry.