Embodied AI 101
110 episodes — Page 2 of 3
LATENT: Teaching a Humanoid to Play Tennis from Imperfect Data
May 19, 202620 min
CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models
May 19, 202642 min
World Action Models: The Next Frontier in Embodied AI
May 19, 202636 min
Training a Whole-Body Control Foundation Model
May 18, 202639 min
DexJoCo: A Unified Benchmark for Task-Oriented Dexterous Manipulation
May 18, 202643 min
MMSkills: Building Multimodal Skill Libraries for Visual Agents
May 18, 202619 min
PhysBrain 1.0 VLA (TwinBrainVLA): Dual-Brain Vision-Language-Action with Physics-Grounded Learning
May 18, 202625 min
MolmoAct2-LIBERO: An Open Vision-Language-Action Model for Robotics
May 17, 202638 min
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Diffusion Transformers
May 17, 202620 min
WildClawBench: A Real-World, Long-Horizon Benchmark for AI Agents
May 17, 202632 min
MCP-Cosmos: Bring Your Own World Model
May 17, 202624 min
OpenAI o1: Teaching LLMs to Think Slow and Deep
May 17, 202614 min
The Llama 3 Herd of Models
May 17, 202632 min
LATENT: Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data
May 17, 202631 min
AnyFlow: Any-Step Video Diffusion for Predictive World Modeling
May 14, 202613 min
# Robotics: The Endgame
May 14, 202634 min
Claw-Eval: Toward Trustworthy and Transparent Evaluation of Autonomous Agents
Apr 8, 202628 min
LIBERO-Para: Paraphrase Robustness in Robotic Manipulation
Apr 8, 202632 min
YOR: Your Own Mobile Manipulator for Generalizable Robotics
Apr 7, 202627 min
EgoSim: Egocentric World Simulator for Embodied Interaction Generation
Apr 7, 202650 min
Accelerating Video World Models: From Generative Videos to Real-Time Simulators
Apr 7, 202639 min
From Tokens to Thoughts: Continuous Latent Reasoning in Large Models and Robot Control
Apr 7, 202626 min
CaP-X: Coding Agents for Physical eXecution
Apr 6, 202613 min
DoRA: Weight-Decomposed Low-Rank Adaptation
Apr 6, 202639 min
AI Model Collapse: What Happens When AI Trains on Its Own Outputs
Apr 6, 202629 min
PhAIL: Benchmarking Vision-Language-Action Models on Real-World Bin-Picking
Apr 5, 202633 min
Co-training Large Behavior Models: Data Modalities and Training Strategies for Robot Manipulation
Apr 5, 202628 min
HyDRA: Hybrid Memory for Dynamic Video World Models
Apr 5, 202621 min
# WildWorld: Dynamic World Modeling with Actions and Explicit State
Apr 4, 202632 min
Omni-WorldBench: Evaluating Interactive 4D World Models
Apr 4, 202639 min
SIMART: From Static Meshes to Sim-Ready Articulated Models
Apr 4, 202638 min
EgoSim: An Egocentric World Simulator for Embodied Interaction
Apr 4, 202636 min
Digit's New Motor Cortex: Sim-to-Real RL for Whole-Body Control
Apr 3, 202631 min
EgoNav: Diffusion-Based Humanoid Navigation from Human Egocentric Video
Apr 3, 202642 min
CaP-X: A Code-as-Policy Framework for Robot Manipulation
Apr 3, 202613 min
Embodied Intelligence Breakthrough: Generalist AI’s GEN-1 Robots
Apr 2, 202615 min
CaP-X: LMs' First Physical Exam
Apr 2, 202622 min
AI Model Collapse: The Danger of Training on AI-Generated Data
Mar 31, 202631 min
High-Level Automated Reasoning with Qwen2.5-7B
Mar 31, 202627 min
Co-Training Large Behavior Models: Multimodal Data for Robot Manipulation
Mar 31, 202633 min
HyDRA: Hybrid Memory for Dynamic Video World Models
Mar 30, 202635 min
DexWM: Leveraging Human Videos for Dexterous Robot World Models
Mar 30, 202631 min
World Models in Robotics
Mar 29, 202626 min
SIMART: Decomposing Monolithic Meshes into Sim-Ready Articulated Assets
Mar 28, 202645 min
LeWorldModel: A Stable JEPA World Model from Pixels
Mar 28, 202613 min
World Models for Robots: The Next Big Leap?
Mar 27, 202620 min
Harnessing Long-Running AI in Embodied Systems
Mar 27, 202627 min
HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations
Mar 26, 202617 min
TurboQuant: Redefining AI Efficiency with Extreme Compression
Mar 26, 202620 min
DexWM: Learning Dexterous Object Manipulation from Human Videos
Mar 25, 202632 min