Robotics & World Models Reading Club 18: Is Latent All You Need for World Action Models? & Causal World Models. SF 07/18

Robotics & World Models Reading Club 18: Is Latent All You Need for World Action Models? From V-JEPA to DreamZero, FastWAM, and ImageWAM & Causal World Models For Real-World Intelligence — San Francisco 07/18 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 DeepMind, NVIDIA, Stanford, UC Berkeley, Dyna, Physical Intelligence, Tesla, Generalist, Rhoda AI, and leading Bay Area robotics startups. Hosted by Junfan Zhu & Aurora Feng. Reading Club 18's Core Theme Keynote 1: Is Latent All You Need for World Action Models? From V-JEPA to DreamZero, FastWAM, and ImageWAM Keynote by: Guanming Wang & Bill (General Instinct, YC P26) World Action Models (WAMs) have recently emerged as a promising paradigm for embodied AI, enabling robots to reason about future observations and actions jointly. While early approaches such as DreamZero rely on generative video prediction to learn rich world representations, more recent methods like FastWAM and ImageWAM suggest that explicitly generating future videos may not be necessary. Instead, predicting and reasoning over latent world representations could be sufficient for effective action generation. In this talk, we revisit this question through the lens of representation learning. Starting from V-JEPA, we discuss the philosophy of predictive latent representations, followed by DreamZero, which unifies future video and action prediction, and finally recent efficient WAMs including FastWAM and ImageWAM, which increasingly shift computation from pixel generation to latent reasoning. We will compare their design choices, discuss the trade-offs between latent prediction and video generation, and explore what information a latent world representation must contain to support robust robotic decision making. Rather than presenting individual papers in isolation, this talk aims to provide a unified perspective on the evolution of World Action Models and examine an open research question for the community: Do robots really need to generate future videos, or is learning the right latent representation enough? Keynote 2: Causal World Models For Real-World Intelligence Aether AI has raised $20M to build causal world models that understand mechanisms. Keynote by Biwei Huang (Professor at UCSD) Pre-Readings Location San Francisco (Downtown) Date & Time Saturday, July 18, 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 – 4:30 PM Keynote 1 by Guanming Wang & Bill (General Instinct, YC P26) Keynote 2 by Biwei Huang, Professor UCSD (https://biweihuang.com/) Online access via Zoom: TBD YouTube Recording: TBD (We are looking for recording volunteers) 4:30 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 #reading-club-20-0725: Agentic Robotics Models (ENPIRE and Cap-X), Mountain View 07/25 Session 20 Luma: https://luma.com/5ltk12w5 #SIGGRAPH-reading-club-19-0722: SIGGRAPH x Saturday Robotics — World Models for Robotics: Bridging Graphics, Simulation & Physical Intelligence | Reading Club 19, LA 07/22 Session 19 Luma: https://luma.com/yh2212ac Past events #reading-club-17-0711: Soft Tactile-Centric Multimodal Intelligence Toward Safe and Dexterous Manipulation. SF 07/11 Session 17 Luma: https://luma.com/e53zawq2 #reading-club-16-0704: The Embodied AI Hardware Stack — Supply Chain, Sensors, and the Data Flywheel — SF 07/04 Session 16 Luma: https://luma.com/cgzyfpeb #reading-club-15-0627: Scaling Touch: Flexible Tactile Skin for Dexterous Manipulation Bingha