Embodied AI 101

Shaoqing Tan

Stay in the loop on research in AI and physical intelligence.

Episodes · 25

When the Command Disappears: What Counts as Robot Intelligence?

Oct 3, 2026 · 28m

Fast Plans Are Not Enough: Does the Robot Actually Use Its Plan?

Oct 2, 2026 · 30m

Atlas's New Hands: Built to Learn, Not Just to Look Human

Oct 2, 2026 · 10m

Astra Gets a Body: What Zero-Shot Humanoid Control Actually Transfers

Oct 1, 2026 · 28m

Physical Coding: Robots That Check Their Work—and Keep the Fixes

Sep 30, 2026 · 29m

SpatialClaw: Give the VLM a Geometry Notebook

Sep 30, 2026 · 26m

Real-Time EXPO-FT: Slow VLA, Fast Corrections, Better Control

Sep 29, 2026 · 29m

Aether: From Plausible Futures to Feasible Robot Plans

Sep 29, 2026 · 28m

ARLI: Fixing the Missing State in Asynchronous Robot RL

Sep 28, 2026 · 27m

Flex-π: Teach Geometry, Choose How Much to Imagine

Sep 28, 2026 · 29m

SkipVLA: Let the Planner Move, Let the VLA Manipulate

Sep 27, 2026 · 28m

ForeDrive: A World Model Is Only Useful If It Changes the Plan

Sep 27, 2026 · 28m

DO AS I DO: Making Human Video Executable

Sep 26, 2026 · 29m

GAM: Ground the Target Before You Learn the Action

Sep 26, 2026 · 30m

Tune Slowly, Control Quickly: Learning a Better Robot Navigation Stack

Sep 25, 2026 · 28m

THAW-VLA: World-Model Features Without World-Model Latency

Sep 24, 2026 · 29m

Joga: Why a Soccer Humanoid Needs to Control Its Gaze

Sep 24, 2026 · 28m

AthenaZero: Why Dynamic Manipulation Starts With Lower Inertia

Sep 23, 2026 · 29m

FROA-Drive and the Hard Part of Targeted Policy Repair

Sep 23, 2026 · 29m

Teach the Robot Where to Act—Then Make It Fast

Sep 22, 2026 · 28m

HEAR: The Sound Your Robot Missed Between Actions

Sep 22, 2026 · 28m

VS-Splat: Learning Where 3D Detail Belongs

Sep 20, 2026 · 29m

Spatial Search Comes to Quest — Beyond Pretty Gaussian Splats

Sep 20, 2026 · 13m

Occamy-1.0: Teaching a 35B Agent to Finish the Job

Sep 19, 2026 · 30m

Helix 2.5: The House Changed. The Policy Didn't.

Sep 18, 2026 · 12m