Alex Smola

Submodular benchmark selection: code and assembled score matrices from the paper (Smola, 2026).

Fork of Apache MXNet 2.0 — runs legacy MXNet code on CUDA 13 / Blackwell (sm_120) GPUs and native Apple Silicon CPU.

Native macOS PDF presenter with a real second-screen / presenter view (Keynote-style) for Beamer and plain PDF decks.

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 400 universities from 60 countries including Stanford, MIT, Harvard, and Cambridge.

Dive into Deep Learning - Quarto rebuild

A common bricks library for building scalable and portable distributed machine learning.

Blackwell patches

No description.

Automate your research.

RL-first post-training framework for large models.

The fastest repo in history to surpass 50K stars ⭐, reaching the milestone in just 2 hours after publication. Better Harness Tools, not merely storing the archive of leaked Claude Code but make real things done. Now rewriting in Rust using oh-my-codex.

This repo contains static site content for www.ceph.io

Ancient SVM code in Matlab

Collector for blog comments

Tying up all components around to deliver a solid and integrated data environment powered by AWS services.

Dive into Deep Learning in 1 Day at ODSC 2019

:triangular_ruler: A flexible two-column Jekyll theme. Perfect for personal sites, blogs, and portfolios hosted on GitHub or your own server.

Jekyll theme based on Grayscale Start Bootstrap theme