A NEW ARTICLE 🔥🔥 The first article of Deep Learning Revision Research Blog(introduced recently) is out: "The Transformer Blueprint: A Holistic Guide to the Transformer Neural Network Architecture". In the article, we discuss the core mechanics of transformer neural

Great lectures on deep generative modelling, covering a whole bunch of topics, model families, and learning algorithms in generative models space. And applications in vision and natural language processing, and reinforcement learning.

Deep Generative Models Lectures: videos, slides, notes, papers https://t.co/Ssvh86lIze

Great lectures on deep generative modelling, covering a whole bunch of topics, model families, and learning algorithms in generative models space. And applications in vision and natural language processing, and reinforcement learning.

https://t.co/sYGwkDiRJa

Your VLMs/VLAs have hidden potential. Sparse Attention Vectors (SAVs) unlocks few-shot, mechanistically interpretable test-time adaptation—beating LoRA with ~20 heads. 🚀 See you today #ICCV2025 🌺 📍Poster #254 (10/21, Session 1) @berkeley_ai @CMU_Robotics @MITIBMLab Links:

Claude Skills shows performance benefits from leveraging LLM skill catalogs at inference time. Our previous work (linked under thread 5/5) showed the same 6 months ago! 🌟Our new work, STAT, shows that leveraging skills during training can greatly help too‼️, e.g., Qwen can

Videos: https://t.co/DxagpWetUF Code:

Applied Machine Learning - Cornell CS5785 "Starting from the very basics, covering all of the most important ML algorithms and how to apply them in practice. Executable Jupyter notebooks (and as slides)". 80 videos. All publicly available.

Course lectures: cme295 stanford edu/

[New course] Transformers & Large Language Models, CME 295 Stanford Yet another excellent course on transformers and large language models with a consolidated curriculum starting right away from transformers. Topics/lectures: - Intro to transformers - Transformer-based models &

Just crossed 100+ citations...🥳🥳

Exactly the same 2 courses I thought seeing the post. There are more across other schools, look at: - advanced NLP at CMU( https://t.co/jvyGAeBvAb) - new inference class of its kind in academia CMU ( https://t.co/kQOfe4s7jw) - LLM systems CMU( https://t.co/dfrfS2ywdB) - large

When Karpathy drops a nano repo, X timeline is great again! Everyone is basically happy.

Statistics 110: Probability - Harvard Inarguably, one of the classic/world's best probability courses on the web!!

https://t.co/xeAus3LmXd

An excellent technical guide on LLM post-raining covering SFT(supervised finetuning), RL rewards such as RLHF/human preferences, RLAIF/constitutional-AI, RLVR/verifiable outcomes, process-supervised and rubric rewards. Also covers common RL training algorithms from PPO, GRPO, and

Deep learning course by legendary Andrew Ng is public now. New 2025 lectures are out!!

Thanks for writing this piece @johnschulman2. Very insightful and lots of practical findings. https://t.co/fwutv1Tfbj

LoRA Without Regret - Recent Blog from Thinking Machines TL/DR: LoRA actually matches full supervised fine-tuning(SFT) when you get the details right. Nearly same sample efficiency, loss(or better), same final performance. Some plain points: - Apply LoRA to ALL layers,

Thanks for using the visual, @ColdFusion_TV. I am a big fan of your tech videos. The amount of work you put into research shows in the videos.