Embodied AI 101
By Shaoqing Tan
Listen to a podcast, please open Podcast Republic app. Available on Google Play Store and Apple App Store.
Image by Shaoqing Tan
Category: Technology
Open in Apple Podcasts
Open RSS feed
Open Website
Rate for this podcast
Subscribers: 0
Reviews: 0
Episodes: 67
Description
Stay in the loop on research in AI and physical intelligence.
| Episode | Date |
|---|---|
|
AlexNet: The Deep Convolutional Network That Transformed Vision
|
May 23, 2026 |
|
A Few Useful Things to Know About Machine Learning
|
May 23, 2026 |
|
SimToolReal: A Universal Dexterous Tool-Use Policy
|
May 23, 2026 |
|
Mimic-Video: Learning Physics Priors from Web-Scale Video for Robot Dexterity
|
May 23, 2026 |
|
Deep Residual Learning for Image Recognition (ResNet)
|
May 23, 2026 |
|
Attention Is All You Need – The Transformer Revolution
|
May 23, 2026 |
|
NVIDIA Cosmos: World Foundation Models for Physical AI
|
May 20, 2026 |
|
LATENT: Teaching a Humanoid to Play Tennis from Imperfect Data
|
May 19, 2026 |
|
CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models
|
May 19, 2026 |
|
World Action Models: The Next Frontier in Embodied AI
|
May 19, 2026 |
|
Training a Whole-Body Control Foundation Model
|
May 18, 2026 |
|
DexJoCo: A Unified Benchmark for Task-Oriented Dexterous Manipulation
|
May 18, 2026 |
|
MMSkills: Building Multimodal Skill Libraries for Visual Agents
|
May 18, 2026 |
|
PhysBrain 1.0 VLA (TwinBrainVLA): Dual-Brain Vision-Language-Action with Physics-Grounded Learning
|
May 18, 2026 |
|
MolmoAct2-LIBERO: An Open Vision-Language-Action Model for Robotics
|
May 17, 2026 |
|
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Diffusion Transformers
|
May 17, 2026 |
|
WildClawBench: A Real-World, Long-Horizon Benchmark for AI Agents
|
May 17, 2026 |
|
MCP-Cosmos: Bring Your Own World Model
|
May 17, 2026 |
|
OpenAI o1: Teaching LLMs to Think Slow and Deep
|
May 17, 2026 |
|
The Llama 3 Herd of Models
|
May 17, 2026 |
|
LATENT: Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data
|
May 17, 2026 |
|
AnyFlow: Any-Step Video Diffusion for Predictive World Modeling
|
May 14, 2026 |
|
# Robotics: The Endgame
|
May 14, 2026 |
|
Claw-Eval: Toward Trustworthy and Transparent Evaluation of Autonomous Agents
|
Apr 08, 2026 |
|
LIBERO-Para: Paraphrase Robustness in Robotic Manipulation
|
Apr 08, 2026 |
|
YOR: Your Own Mobile Manipulator for Generalizable Robotics
|
Apr 07, 2026 |
|
EgoSim: Egocentric World Simulator for Embodied Interaction Generation
|
Apr 07, 2026 |
|
Accelerating Video World Models: From Generative Videos to Real-Time Simulators
|
Apr 07, 2026 |
|
From Tokens to Thoughts: Continuous Latent Reasoning in Large Models and Robot Control
|
Apr 07, 2026 |
|
CaP-X: Coding Agents for Physical eXecution
|
Apr 06, 2026 |
|
DoRA: Weight-Decomposed Low-Rank Adaptation
|
Apr 06, 2026 |
|
AI Model Collapse: What Happens When AI Trains on Its Own Outputs
|
Apr 06, 2026 |
|
PhAIL: Benchmarking Vision-Language-Action Models on Real-World Bin-Picking
|
Apr 05, 2026 |
|
Co-training Large Behavior Models: Data Modalities and Training Strategies for Robot Manipulation
|
Apr 05, 2026 |
|
HyDRA: Hybrid Memory for Dynamic Video World Models
|
Apr 05, 2026 |
|
# WildWorld: Dynamic World Modeling with Actions and Explicit State
|
Apr 04, 2026 |
|
Omni-WorldBench: Evaluating Interactive 4D World Models
|
Apr 04, 2026 |
|
SIMART: From Static Meshes to Sim-Ready Articulated Models
|
Apr 04, 2026 |
|
EgoSim: An Egocentric World Simulator for Embodied Interaction
|
Apr 04, 2026 |
|
Digit's New Motor Cortex: Sim-to-Real RL for Whole-Body Control
|
Apr 03, 2026 |
|
EgoNav: Diffusion-Based Humanoid Navigation from Human Egocentric Video
|
Apr 03, 2026 |
|
CaP-X: A Code-as-Policy Framework for Robot Manipulation
|
Apr 03, 2026 |
|
Embodied Intelligence Breakthrough: Generalist AI’s GEN-1 Robots
|
Apr 02, 2026 |
|
CaP-X: LMs' First Physical Exam
|
Apr 02, 2026 |
|
AI Model Collapse: The Danger of Training on AI-Generated Data
|
Mar 31, 2026 |
|
High-Level Automated Reasoning with Qwen2.5-7B
|
Mar 31, 2026 |
|
Co-Training Large Behavior Models: Multimodal Data for Robot Manipulation
|
Mar 31, 2026 |
|
HyDRA: Hybrid Memory for Dynamic Video World Models
|
Mar 30, 2026 |
|
DexWM: Leveraging Human Videos for Dexterous Robot World Models
|
Mar 30, 2026 |
|
World Models in Robotics
|
Mar 29, 2026 |
|
SIMART: Decomposing Monolithic Meshes into Sim-Ready Articulated Assets
|
Mar 28, 2026 |
|
LeWorldModel: A Stable JEPA World Model from Pixels
|
Mar 28, 2026 |
|
World Models for Robots: The Next Big Leap?
|
Mar 27, 2026 |
|
Harnessing Long-Running AI in Embodied Systems
|
Mar 27, 2026 |
|
HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations
|
Mar 26, 2026 |
|
TurboQuant: Redefining AI Efficiency with Extreme Compression
|
Mar 26, 2026 |
|
DexWM: Learning Dexterous Object Manipulation from Human Videos
|
Mar 25, 2026 |
|
FlashAttention-3: Fast & Accurate Attention with Asynchrony & Low-Precision
|
Mar 25, 2026 |
|
When AI Trains on Its Own Output: The Model Collapse Problem
|
Mar 25, 2026 |
|
MolmoBot: A Vision-Language Model for Zero-Shot Robot Manipulation
|
Mar 24, 2026 |
|
LeWorldModel: Stable End-to-End JEPA from Pixels
|
Mar 24, 2026 |
|
EgoVerse: An Egocentric Data Ecosystem for Scaling Robot Learning
|
Mar 24, 2026 |
|
HSImul3R: Physics-Driven Reconstruction of Human–Scene Interactions
|
Mar 24, 2026 |
|
MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation
|
Mar 23, 2026 |
|
DreamZero: World Action Models Are Zero-Shot Policies
|
Mar 23, 2026 |
|
Kinema4D: A 4D Generative Simulator for Embodied AI
|
Mar 23, 2026 |
|
VEGA-3D: Teaching multimodal LLMs spatial reasoning through video generation
|
Mar 23, 2026 |