The paper introduces SmartSDG, an automated pipeline using NVIDIA Isaac Sim and Physically-Based Shading to optimize synthetic-to-real domain adaptation. It shows that indirect lighting and complex backgrounds improve object detection by preserving surface textures and reducing false positives, outperforming conventional direct-light synthetic data.
arxiv
arXiv cs.AI
·
79d ago
·
src: 82d ago
·
research
SmartSDG Pipeline Enhances Syn-to-Real Object Detection
from English
Importance 2/3
New harness with differentiators
arXiv cs.AI
NVIDIA
Evaluation & benchmarks
Multimodal
Related articles
lab
NVIDIA Research
·
45d ago
·
26 views
NVIDIA introduces Spatial-IQ, a hierarchical diagnostic framework for multimodal model spatial reasoning
Researchers at NVIDIA have introduced Spatial-IQ, a diagnostic framework designed to deconstruct the spatial intelligence of multimodal large language models (MLLMs). Unlike existing benchmarks that treat models as black boxes, this approach decomposes object counting in stacked 3D structures into nine perceptual and cognitive sub-tasks aligned with human developmental stages.
media
Hugging Face Forums
·
18d ago
·
18 views
Unified GGUF and llama.cpp fork enable audio and video for Nemotron-3-Nano-Omni
The author addresses silent failures in popular GGUF versions of Nemotron-3-Nano-Omni-30B, where audio and video inputs were ignored due to incomplete projector files and missing inference graphs. To fix this, a unified mmproj file containing the vision tower, full Parakeet/FastConformer audio encoder, and temporal video embedder has been released alongside a specialized llama.cpp fork.
media
Hugging Face Forums
·
18d ago
·
12 views
Zero-shot Nemotron 3.5 Lightning Omni adds vision and audio via geometry match
The author has created Nemotron 3.5 Lightning-Omni by attaching pre-trained projectors from NVIDIA’s Nemotron-3-Nano-Omni to the text-only Nemotron 3.5 Lightning model, enabling image and audio understanding without any additional training.
arxiv
arXiv cs.CL
·
24d ago
·
16 views
Nemotron-3-Embed closes commercial tax gap in MuSiQue retrieval benchmarks
A new audit of multi-hop retrieval benchmarks reveals that NVIDIA's Nemotron-3-Embed-8B has closed the performance gap between commercially licensed embedders and the non-commercial NV-Embed-v2 anchor on the MuSiQue benchmark. Released on July 16, 2026, this model is the only commercially licensed, free-to-self-host option that performs indistinguishably from the academic standard.
lab
Microsoft Research Blog
·
30d ago
·
43 views
Microsoft Research introduces MindTopo benchmark for evaluating VLMs' spatial reasoning
Microsoft Research has introduced MindTopo, a new benchmark designed to evaluate whether multimodal large language models possess topological intuition regarding connectivity, enclosure, order, separation, and knots.