Sveriges mest populära poddar
Embodied AI 101
VetenskapTeknologi

VEGA-3D: Teaching multimodal LLMs spatial reasoning through video generation

32 min•23 mars 2026
A plug-and-play framework extracts implicit 3D priors from video diffusion models to enhance multimodal LLMs with spatial reasoning capabilities, enabling improved geometric scene understanding and embodied decision-making without explicit 3D supervision.

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
SIMART: Decomposing Monolithic Meshes into Sim-Ready Articulated Assets
•45 min
LeWorldModel: A Stable JEPA World Model from Pixels
•14 min

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