Saturday Robotics & World Models Reading Club 04: Abstractions of the Physical World for Decision-Making — San Francisco
Robotics & World Models Reading Club 04: Abstractions of the Physical World for Decision-Making
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, 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.
Venue provided by Savant, a community for technologists tackling civilizational-scale tech, helping founders navigate the -1 to 0 phase with hardware labs, office hours, and an elite peer network.
Reading Club 04's Core Theme
Many approaches to world models have emerged in recent years, from generative video models and joint embedding methods to structured simulators. Yet it remains unclear which representations, if any, will ultimately support general embodied intelligence.
In this talk, Siming He (PhD Candidate, UC Berkeley) will guide us to revisit the notion of a “world model” from a statistical and systems perspective, viewing it as a necessarily simplified abstraction of the physical world for downstream decision-making. He will use this lens to discuss how different representations capture distinct aspects of the functional requirements for embodied intelligence, including semantics, dynamics, and interaction.
He will share a few tentative perspectives on the limitations and practical usefulness of current world models, and highlight open questions around generalization and representation design. The goal is to foster thoughtful discussion and encourage a more careful exploration of this space.
Pre-Readings
1. 3D Representations for World Modeling
→ Examples of structured 3D representations that capture geometry, semantics, and interaction affordances for manipulation.
Reconstructing Hand-Held Objects in 3D from Images and Videos
SAM3D: Segment Anything in 3D
Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration
2. Low-Dimensionality & Redundancy in Learning
→ Suggests why world models can still generalize effectively to downstream tasks despite the complexity of the real world
Many perception tasks are highly redundant functions of their input data (arXiv)
The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold — PNAS
3. Biological Inspiration
→ Illustrates predictive representations and forward simulation in biological systems as a form of world modeling
Neural Ensembles in CA3 Transiently Encode Paths Forward of the Animal at a Decision Point
Control strategies in object manipulation tasks
4. Foundations of Modeling
→ Classic perspective on models as simplified “small worlds” designed for decision-making under uncertainty
The Foundations of Statistics Ch 5.5 Small Worlds — Leonard J. Savage
Location
San Francisco (Downtown)
Date & Time
Saturday, May 9, 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 by Siming He (UC Berkeley)
Online access via Zoom: TBD
YouTube Recording: TBD (We are looking for recording volunteers)
3:00 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.
Past events
#reading-club-03-0411
Session 03 Luma: https://luma.com/561xgirg
Reading Club 03 Review: https://x.com/junfanzhu98/status/2043243484568768519?s=20
Event summary & photos: https://x.com/junfanzhu98/status/2043245823933477004?s=20
LinkedIn more photos: https://www.linkedin.com/posts/junfan-zhu_robotics-world-model-reading-club-03-robotic-ugcPost-7448991959093932032-Vo5d?utm_source=share&utm_medium=member_desktop&rcm=ACoAABxP-p0BpUNGDf347aKh_1uJAPzG4er0As8
#reading-club-02-0404
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
Event photos: https://x.com/junfanzhu98/status/2040717084972245341?s=20
LinkedIn more photos: https://www.linkedin.com/posts/junfan-zhu_robotics-world-model-reading-club-02-hot-ugcPost-7446465600723509248-1qbj?utm_source=share&utm_medium=member_desktop&rcm=ACoAABxP-p0BpUNGDf347aKh_1uJAPzG4er0As8
#reading-club-01-0328
Session 01 Luma: https://luma.com/8s4w1wu6
Reading Club 01 Review: https://x.com/junfanzhu98/status/2038153945219305812
Event photos (liked by Yann LeCun on X): https://x.com/junfanzhu98/status/2038161288090779985
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.