Embodied AI 101
Stay in the loop on research in AI and physical intelligence..
Shaoqing Tan
100 episodesEN
Show overview
Embodied AI 101 has published 100 episodes during 2026. That works out to roughly 50 hours of audio in total. Releases follow a near-daily cadence.
Episodes typically run twenty to thirty-five minutes — most land between 25 min and 36 min — though episode length varies meaningfully from one episode to the next. None of the episodes are flagged explicit by the publisher. It is catalogued as a EN-language Technology show.
The show is actively publishing — the most recent episode landed earlier today, with 100 episodes already out so far this year. Published by Shaoqing Tan.
Episodes
100
Started
2026
Median length
29 min
Cadence
Near-daily
From the publisher
Stay in the loop on research in AI and physical intelligence.
Latest Episodes
View all 100 episodesRobotic World Model: Learning to Simulate for Robust Robot Control
Jun 12, 202619 min
AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
Jun 10, 202623 min
ArtiFixer: Few-Step Diffusion for 3D Scene Reconstruction
Jun 10, 202626 min
Deployment-Time Memorization in Foundation-Model Agents
Jun 10, 202639 min
Adversarial Machine Learning: Taxonomy, Threat Models, and Mitigation Strategies in Deep Neural Networks
Jun 9, 202634 min
SoCRATES: Evaluating LLM Mediators in Conflict Scenarios
Jun 9, 202620 min
Unembedding Matrix as a Feature Lens: Unlocking Better Text Embeddings
Jun 9, 202624 min
LeanMarathon: Autonomous Formalization of Math Proofs on Erdős Problems
Jun 8, 202627 min
Deep Research Agents: Survey and Roadmap for Autonomous AI Research
Jun 8, 202637 min
Cosmos 3: Omnimodal World Models for Physical AI
Jun 7, 202628 min
Humanoid-GPT: GPT-Style Transformer for Zero-Shot Dynamic Humanoid Control
Jun 7, 202622 min
Bending Paper, Shaping Dexterity: The Robotic Origami Challenge
Jun 5, 202629 min
GraspGen-X: A Foundation Model for Zero-Shot 6-DoF Grasping
Jun 5, 202635 min
When Does Deep RL Beat Calibrated Baselines?
Jun 4, 202615 min
Training Deep Networks as Random Effects: An Optimization–Inference Duality
Jun 4, 202621 min
Generative Depth Supervision for Embodied Vision-Language Models
Jun 2, 202628 min
PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation
Jun 1, 202630 min
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
May 31, 202632 min
LT2: Linear-Time Looped Transformers
May 31, 202642 min
One Learning Rate Doesn't Fit All: Layerwise Spectral Scheduling for Transformers
May 31, 202626 min
© 2026 Shaoqing Tan