kNN
kNN at Beyond Market Intelligence is a file of 3 stories. The newest of them: “Explore a new open-source library standardizing 3D point cloud models with PyTorch”, “Whitetree: smarter nearest-neighbor search for streaming sensor data”, and “From geospatial data to graph networks, City2Graph simplifies urban analysis.”. Point cloud models have long been trapped inside research codebases with custom build steps and shifting checkpoints. A dynamic exact index for streaming nearest-neighbor search is rare, and whitetree makes a strong case for it. Acme AI is the next-generation, AI-powered spreadsheet platform built to replace Excel and redefine how analysts, data scientists, and enterprise teams work… The list below is every kNN story on Beyond Market Intelligence, newest first.

Explore a new open-source library standardizing 3D point cloud models with PyTorch
Point cloud models have long been trapped inside research codebases with custom build steps and shifting checkpoints. Torch-pointcloud changes that. It wraps multiple architectures, PointNet++, KPConv, Point Transformer v3, and more, behind a single `create_model()` factory, reusing core components like KNN and FPS rather than reinventing them. Weights are on Hugging Face, installation uses pre-built wheels, and benchmarks match original metrics. It is still alpha, but the goal is a library you can actually `pip install` and trust.

Whitetree: smarter nearest-neighbor search for streaming sensor data
A dynamic exact index for streaming nearest-neighbor search is rare, and whitetree makes a strong case for it. The key insight: scipy's cKDTree has a fixed per-query cost, so maintaining several small trees beats rebuilding one large one. The numbers are compelling, especially the 1,100 steps per second on a 200k-point sliding window. It's a practical, well-measured contribution, and the open question about missed benchmarks is worth exploring.

From geospatial data to graph networks, City2Graph simplifies urban analysis.
Geospatial data is messy, and City2Graph's new paper makes a clean argument for why heterogeneous graphs beat flat tables. The library turns buildings and street segments into analysis-ready nodes and edges, then pushes them straight into PyTorch Geometric. That is a practical bridge between urban morphology and graph neural networks. It is not about hype; it is about making the workflow simpler. For anyone tired of wrestling with geometry and attributes across conversions, this feels like a step toward a more accessible, future-focused toolkit.