Podcast Episodes
Back to SearchMolmoBot: A Vision-Language Model for Zero-Shot Robot Manipulation
Vision-language model (VLM) for zero-shot robot manipulation, trained entirely in simulation without real-world data; achieves 79.2% success rate on …
6 months, 3 weeks ago
LeWorldModel: Stable End-to-End JEPA from Pixels
A stable end-to-end Joint Embedding Predictive Architecture (JEPA) trained directly from pixels that enables robust world modeling for embodied AI sy…
6 months, 3 weeks ago
EgoVerse: An Egocentric Data Ecosystem for Scaling Robot Learning
Ecosystem with over 1300 hours of egocentric human video data spanning 240 scenes and 2000+ tasks, designed for scalable robot policy training via be…
6 months, 3 weeks ago
HSImul3R: Physics-Driven Reconstruction of Human–Scene Interactions
Physics-in-the-loop bi-directional optimization pipeline reconstructing stable, simulation-ready 3D human-scene interactions from casual videos, depl…
6 months, 3 weeks ago
MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation
Open-source suite of large-scale simulation environments and benchmarks designed for advancing end-to-end learning in robot navigation and manipulati…
6 months, 3 weeks ago
DreamZero: World Action Models Are Zero-Shot Policies
Introduces World Action Models (WAMs), a family of 14B-parameter autoregressive diffusion models that jointly predict video and robotic actions to en…
6 months, 3 weeks ago
Kinema4D: A 4D Generative Simulator for Embodied AI
An action-conditioned 4D generative robotic simulator that disentangles precise kinematic control from environmental dynamics, facilitating physicall…
6 months, 3 weeks ago
VEGA-3D: Teaching multimodal LLMs spatial reasoning through video generation
A plug-and-play framework extracts implicit 3D priors from video diffusion models to enhance multimodal LLMs with spatial reasoning capabilities, ena…
6 months, 3 weeks ago