Don't miss out on this excellent development! Check it out now! GitHub: https://t.co/9BPlKjPHYD #CodeSharing #TurboFuzzLLM

Taking GPTFuzz to the next level, we introduce TurboFuzzLLM, a significantly improved and more efficient method. (Source: https://t.co/3lU5ZWSKw7) -- 3x reduction in queries while generating 2x more jailbreaking templates automatically

Why choose TurboFuzzLLM? 🤩 - Highlighted in recent benchmarking paper on jailbreaking,  "Regarding LLM jailbreaking , GPTFuzz emerged as the most effective given the experiment budget. " (Source: https://t.co/UhRseoRieb) - Our TurboFuzzLLM Taking GPTFuzz to the next level

🚀 Exciting Code Release Alert! 🚀 GitHub: https://t.co/DJytC3iOaF Get ready to explore the latest code sharing with TurboFuzzLLM! 🌟 -- BEST template based LLM jailbreaking method! https://t.co/9BPlKjPHYD

TextAttack: TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://t.co/044cbt6Gj0 Lang: Python ⭐️ 2401 Author: @Qdatalab #MachineLearning https://t.co/ioSDMvVH76

Congratulations to the wonderful work, Zeming!

ML Course Notes (3000⭐️) ICYMI, this repo provides detailed notes on deep learning topics. I'll be releasing the first set of notes on Deep Learning for NLP this coming month. Stay tuned! https://t.co/f3G6ARdH11

Reasoning as energy minimization! One of the key points of my recent position paper on autonomous machine intelligence https://t.co/EmT1On8Y9I (and of my 2006 "tutorial on energy-based learning").

On the door of my 10-year-old’s room at home. She made this

MLOps Primer If you are curious about MLOPs and why it matters in designing ML systems, I've put together a collection of my favorite references. Check it out: https://t.co/YrOkyTVxTg

Lie: The world is a zero-sum game. If it bothers you to see other people succeed, you’re definitely not gonna make it. Distance yourself from anyone who spends time bringing others down. Celebrate everyone’s wins and you’ll start winning more. A rising tide lifts all boats.

I remember breaking down to my Ph.D. advisor about how stupid I felt while troubleshooting a problem in my project when she handed me this paper. Years later it is still relevant to young students starting off in Science. It's ok to feel stupid, we all do on a regular basis.

After 2 years of work by 442 contributors across 132 institutions, I am thrilled to announce that the https://t.co/wezEGzDEHt paper is now live: https://t.co/4Yg36EB9Ru. BIG-bench consists of 204 diverse tasks to measure and extrapolate the capabilities of large language models.

Ten years ago, after reading the sandy hook tragedy, I cries for days . This time, could not even read the news on Uvalde tragedy. Just a peek of titles made me into tears. WHY,WHY, after 10years, this type of tragedy happened again?

The Fence @CarnegieMellon

Congrats to my @CMUCompBio colleague Ziv Bar-Joseph's new role @sanofi by taking a leave from CMU. It's wonderful to see many successful computational biologists in academia are going to make such an important impact in industry. I believe in the long run it's great for the field

TextAttack: TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://t.co/044cbt6Gj0 Lang: Python ⭐️ 1849 Author: @Qdatalab #MachineLearning https://t.co/ioSDMvVH76

The past month I've been writing detailed notes for the first 15 lectures of Stanford's NLP with Deep Learning. Notes contain code, equations, practical tips, references, etc. As I tidy the notes, I need to figure out how to best publish them. Here are the topics covered so far:

SGD with momentum can be implemented slightly differently depending on frameworks. For ex, Pytorch uses the 1st equation while Keras uses the 2nd. This only affects scaling of the momentum and learning rate parameters but still papers should ideally mention which one they use.

In case you not knowing this already, OpenAI API ( https://t.co/Y1mFzOR2f7) is open for immediate access now! No wait list any more! 🥳 🥳 🥳