Sveriges mest populära poddar
Embodied AI 101
VetenskapTeknologi

SIMART: Decomposing Monolithic Meshes into Sim-Ready Articulated Assets

45 min•28 mars 2026
Unified MLLM framework with Sparse 3D VQ-VAE that reduces tokens by 70% for efficient part-level decomposition and kinematic prediction in physics-based robotic simulations.

Fler avsnitt av Embodied AI 101

Visa alla avsnitt av Embodied AI 101
AI Model Collapse: The Danger of Training on AI-Generated Data
•32 min
# High-Level Automated Reasoning with Qwen2.5-7B
•28 min
Co-Training Large Behavior Models: Multimodal Data for Robot Manipulation
•33 min
MolmoBot: Opening a New Era of Simulated Training in Robotics
•22 min
HyDRA: Hybrid Memory for Dynamic Video World Models
•36 min
DexWM: Leveraging Human Videos for Dexterous Robot World Models
•31 min
World Models in Robotics
•27 min
MolmoBot: Training Robot Manipulation Entirely in Simulation
•25 min
LeWorldModel: A Stable JEPA World Model from Pixels
•14 min
World Models for Robots: The Next Big Leap?
•20 min

Embodied AI 101 med Shaoqing Tan finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.