Alfredo Canziani
@alfcnz
Musician, math lover, cook, dancer, 🏳️🌈, and an ass prof of Computer Science at New York University
Releasing the Energy-Book 🔋 from its first appendix's chapter, where I explain how I create my figures. 🎨 Feel free to report errors via the issues' tracker, contribute to the exercises, and show me what you can draw, via the discussion section. 🥳 github.com/Atcold/Energy-…
The opportunity gap in AI is more striking than ever. We talk way too much about those receiving $100M or whatever for their jobs, but not enough those asking for <$1k to present their work. For 3rd year in a row, @ml_collective is raising funds to support @DeepIndaba attendees.
Laughable. 😑😑😑 It’s considered unethical playing unethical people. What??? Com’on! 🙄🙄🙄
ICML’s Statement about subversive hidden LLM prompts We live in a weird timeline…
My @NYUDataScience colleague, Carlos Fernandez-Granda, released the 700-page textbook «Probability and Statistics for Data Science», where he condenses 10 years of teaching experience at @NYUniversity. 200 exercises, 102 notebooks, 115 videos! 🥳🥳🥳 ps4ds.net
New Book & Video Series!!! (late 2025) Optimization Bootcamp: Applications in Machine Learning, Control, and Inverse Problems Comment for a sneak peak to help proofread and I'll DM (proof reading, typos, HW problems, all get acknowledgment in book!)
Reinforcement Learning of Large Language Models, Spring 2025(UCLA) Great set of new lectures on reinforcement learning of LLMs. Covers a wide range of topics related to RLxLLMs such as basics/foundations, test-time compute, RLHF, and RL with verifiable rewards(RLVR).
late 1980s, @ylecun and @LeonBottou used amiga 1000 and a bespoke modem to implement and research artificial neural nets using SN-1. the legend was born.
A beautiful paper that goes through Diffusion step by step, explaining the entire math of it from the beginning.
Our latest CS336 Language Modeling from Scratch lectures are now available! View the entire playlist here: youtube.com/playlist?list=…
How can we unlock generalized reasoning? ⚡️Introducing Energy-Based Transformers (EBTs), an approach that out-scales (feed-forward) transformers and unlocks generalized reasoning/thinking on any modality/problem without rewards. TLDR: - EBTs are the first model to outscale the…
To compute the movement of the state x(t), we need to temporally integrate its velocity field ẋ(t). 🤓 The control signal steering angle stays at 0, then 0.05π, then linearly to −0.20π. The vehicle moves along circumferences. Finally, a sweep of initial velocity is performed.
Currently, writing chapter 10, «Planning and control». Physical constrains for the evolution of the state (e.g. pure rotation of the wheels) are encoded through the velocity of the state ẋ = dx(t)/dt, a function of the state x(t) and the control u(t).
Jupytext makes dealing with notebooks a breeze. • allows you to open .PY files as notebooks, enabling partial execution, • gives you the ability to vim your notebooks, and • can pair a notebook with a synchronised .PY textual version for easy diffs. For git, see nbdime.
«Underactuated Robotics» by @RussTedrake Non-linear dynamics + control + optimisation + machine learning, with real robot focus. 🤖🦾🦿 Publicly annotatable textbook + Deepnote notebook using Python bindings for @ToyotaResearch's Drake open-source C++ lib. underactuated.csail.mit.edu
«Detachment» has a hollow and lonely teacher who copes with life by being emotionally untouchable. Yet, in his distance and gentle reserve, he gets closer to those who would have otherwise never trusted him. This movie leaves a bitter sweet taste in the mouth. 🥺🥺🥺
«Radical», a cinematic ode to unconventional teaching, where learning thrives being rooted in student curiosity, who become architects of their own knowledge. Sergio’s pedagogy remarkably echoes mine. The movie resonated deeply with me and evoked a powerful emotional response.