← Back to Videos

JEPA-Anything: One World Model Across Six Domains

Loading video

One world model spanning molecules, cells, fluids, patients, robots and weather, with code released.

World Models Embodied AI JEPA Robot Learning Scientific ML

Category: research

Author: @Charles_Y_Wu

Date: 2026-10-05T00:00:00

Duration: 30.0s

Source: https://x.com/Charles_Y_Wu/status/2107134454762496397

Reference: https://arxiv.org/abs/2609.20800

Odyssey-3: A Foundation World Model for Physical Agents

Odyssey-3: A Foundation World Model for Physical Agents

@odysseyml · 831 views · 2026-09-15

World ModelsFoundation ModelsPhysical AI

Odyssey-3: World Models as Training Grounds for Agents

Odyssey-3: World Models as Training Grounds for Agents

@olivercameron · 581 views · 2026-09-15

World ModelsEmbodied AISimulation

LingBot-World 2.0 Opens Infinite Worlds

LingBot-World 2.0 Opens Infinite Worlds

@robbyant_brain · 590 views · 2026-07-08

World ModelsEmbodied AIInteractive Video

EchoWM: A Drivable World Model, Not Just a Clip

EchoWM: A Drivable World Model, Not Just a Clip

@JinWeiyang18434 · 269 views · 2026-08-24

World ModelsEchoWMJoy-Echo

τ0-VLA: Robot VLA that searches over subtask sequences at test time with a world model

τ0-VLA: Robot VLA that searches over subtask sequences at test time with a world model

@jiqizhixin · 520 views · 2026-08-07

VLAWorld ModelsEmbodied AI

Being-H0.8: Latent Tactile World Action Model

Being-H0.8: Latent Tactile World Action Model

@beingbeyond_ · 356 views · 2026-07-28

Tactile SensingWorld ModelsEmbodied AI

As an Amazon Associate, we earn from qualifying purchases.