4 articles

visión

Index of editorial tags and filtered coverage.

Sep 24, 2026Nvidia

NVIDIA unveils NV-Reason-CT, an open 3D vision-language model for CT scans

NV-Reason-CT (arxiv 2609.27511) pairs a Primus/COLIPRI-style 3D encoder with Qwen3.5-4B and GRPO RL; reports ~0.614 macro-F1 and ~0.871 AUROC on CT-RATE, plus a preliminary ~50% interpretation-time cut claim.

Sep 25, 2023GPT-4V

GPT-4V and the era of visual chat interfaces

Vision in chatbots enabled reasoning over diagrams, screenshots, and scanned documents in one thread.

Dec 10, 2015ResNet

ResNet (2015): residual connections to go deeper

He et al. introduced residual networks that enabled training hundreds of layers and won ILSVRC 2015.

Dec 1, 1989LeCun

Yann LeCun and CNNs for digits: convolutions that learned to see

In the late 1980s–90s, LeCun and colleagues applied convolutional networks to zip-code and check recognition.