Yilun Du

Sameer Dharur

Sameer Dharur is a research scientist on the Cosmos team at NVIDIA, helping to build vision-language-models (VLMs) that reason better about the world. Prior to that, he spent ~4.5 years as a researcher and engineer at Apple specializing in computer vision and natural language processing to solve problems in image and video understanding, question answering, and robotics.

Jing Wang

Wei-Cheng Tseng

Wei-Cheng Tseng is a research scientist at NVIDIA Research. He is also Ph.D. student in University of Toronto. His research interests are computer vision, generative AI applications in physical AI. He received his M.S. and B.S. in Electrical Engineering from National Tsing Hua University.

Website: https://weichengtseng.github.io/

Zhen Dong

MAISI-v2: Accelerated 3D High-Resolution Medical Image Synthesis with Rectified Flow and Region-specific Contrastive Loss

Retrospectives on the Embodied AI Workshop

Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification

Experimental Assessment of Human-Robot Teaming for Multi-Step Remote Manipulation with Expert Operators

Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting

The recent revolution in data-driven methods for weather forecasting has lead to a fragmented landscape of complex, bespoke architectures and training strategies, obscuring the fundamental drivers of forecast accuracy. Here, we demonstrate that state-of-the-art probabilistic skill requires neither intricate architectural constraints nor specialized training heuristics. We introduce a scalable framework for learning multi-scale atmospheric dynamics by combining a directly downsampled latent space with a history-conditioned local projector that resolves high-resolution physics.

Subscribe to