Computer Vision
-
Understanding how PANet shortens the path between low-level and high-level features
16 min read -
A story about a broken printer, visual inductive bias, and why the race endedin a…
5 min read -
DiffuJudge-AV: A Diffusion-Inspired Framework for Calibrated AV Video Evaluation
Large Language ModelsA diffusion-inspired framework for stress-testing and denoising LLM-as-a-Judge pipelines, applied to safety-critical driving video.
19 min read -
How depth estimation, foundation segmentation, and geometric fusion are converging into spatial intelligence
19 min read -
When we try to train a very deep neural network model, one issue that we…
20 min read -
A PyTorch implementation on the YOLOv3 architecture from scratch
24 min read -
The neighborhood of synthetic data
7 min read -
Why specialized models still hold the 30x speed advantage in production environments
19 min read -
A multi-tier approach to segmentation, color correction, and domain-specific enhancement
13 min read -
A history of Transformer artifacts and the latest research on how to fix them
13 min read