NVIDIA Learning and Perception Research

Adaptive Flow Matching for Resolving Small-Scale Physics

7/1/2025

Publication International Conference on Machine Learning (ICML)

RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counter Factual Reasoning

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills

6/1/2025

Publication Robotics: Science and Systems (RSS)

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

FoundationStereo: Zero-Shot Stereo Matching

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Best paper award candidate, Oral

computer-sciencecomputer-vision

Parallel Sequence Modeling via Generalization Spatial Propagation Network (GSPN)

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Scaling Vision Pre-Training to 4K Resolution

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Highlight

SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

3D-MVP: 3D Multiview Pretraining for Robotic Manipulation

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

NaVILA: Legged Robot Vision-Language-Action Model for Navigation

6/1/2025

Publication Robotics: Science and Systems (RSS)

MambaVision: A Hybrid Mamba-Transformer Vision Backbone

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

NVILA: Efficient Frontier Visual Language Models

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation

6/1/2025

Publication Robotics: Science and Systems (RSS)

Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Recreating 1940s Tom and Jerry with Test-Time Training

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Zero-Shot Monocular Scene Flow Estimation in the Wild

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Best paper award candidate, Oral

aicomputer-sciencecomputer-vision

RADIO Amplified: Improved Baselines for Agglomerative Vision Foundation Models

6/1/2025

Publication IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

research.io

Sign up to keep scrolling

Create your feed subscriptions, save articles, keep scrolling.

Already have an account?