OpenFusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation github.com/UARK-AICV/Open… TL;DR: Open-Fusion builds an open-vocabulary 3D queryable scene from a sequence of posed RGB-D images in real-time.

I am looking to hire multiple PhDs/visiting students in this cycle. Topics of interest include: - Neural scene representations for robotics - LLMs as agents - Robot learning - Science of deep learning - Any other topics that can diversify our research portfolio For PhD

Often overlooked in AI, morphological representations are one of the strongest form of prior behind ALL intelligent being - acquired over generations - has no replacement - more fundamental+critical than acquired representations (world models, concepts, etc)

Check out Marco's presentation of NVIDIA GTC on how Nvidia shapes next-gen autonomous driving with foundation models! Super excited to work with the team!

We are thrilled to announce a Special Issue on Visual SLAM in the IEEE Transactions on Robotics (T-RO). Submission deadline: December 15, 2024. We invite contributions on latest advancements on topics related but not limited to: - Robust SLAM - Representations in SLAM (NeRF,

Funding an AV deployment in your community can feel like a big hurdle to jump, but we have resources and guidance to help. 👏 In this 1-hour webinar, learn valuable insights from industry experts on how to secure funding to bring AVs to your community. hubs.ly/Q02zKgy50

Mr. Pedro Domingos This is a country whose leader blatantly says "We lied, we cheated, we stole… we had entire training courses." And thus there's conceited clown like you to spread China hate everywhere. Your self-imagined star-spangled awesomeness doesn't change the fact that

Zizheng was one of our interns at NVIDIA back in summer 2023. Later, when we were considering to make him a FT offer, he chose to join DeepSeek without much hesitance. Back then, the DeepSeek multimodal team only has 3 people. I am still very much impressed by Zizheng’s decision