David Bau

My student Rohit Gandikota is finding that large diffusion models like SDXL can be controlled very precisely with low-rank changes in parameters.

His twitter thread on "Concept Sliders" is also a great survey of current diffusion model controllability work. The nice thing about modern image synthesis is that the results are gorgeous.

Help him spread the word!

https://x.com/RohitGandikota/status/1727410973638852957?s=20

https://sliders.baulab.info/

My student Koyena Pal will be presenting some cool work at #CoNLL2023.

Her Future Lens (https://future.baulab.info) can look a single hidden state of an LLM and see what a transformer is planning, several tokens ahead.

It can make reading the internal states much more intuitive!

Look for us if you'll be in Singapore for EMNLP/BlackboxNLP/CoNLL.

Work with Jiuding Sun, Andrew Yuan, and Byron Wallace.

https://future.baulab.info

https://twitter.com/kpal_koyena/status/1723026282781581380?s=20

Eric Todd has a really interesting new preprint on arXiv:

https://functions.baulab.info

He shows LLMs contain vector representations of functions that compose and apply in diverse contexts.

It could be a powerful tool for understanding reasoning mechanisms within LLMs.

Eric explains more on a twitter thread here

https://x.com/ericwtodd/status/1717277426873766104?s=20

It's his paper of his PhD. Help him spread the word!

@tdietterich@mastodon.social @aaronhertzmann@fediscience.org

People are speculating, "it's over." If so: what a strange way to close down a major property.

https://downdetector.com/status/twitter/

@geomblog@mastodon.social Thanks! Emailing a few qs!

I want to show the NSF there would be broad support+utility for a "National Deep Inference" service for >100b LLMs.

If your research would be enabled by an inference service on open LLMs w API access+overrides to internal activations, params, gradients: please boost this thread!

(I'm also gathering feedback on twitter - more details here:)

https://twitter.com/davidbau/status/1605609105824964611

Had a great time meeting people at #BlackboxNLP and #EMNLP2022 last week. You can see my talk as well as great talks by Lena Voita and Catherine Olsson on youtube here:

@blackboxnlp@youtube.com

@wattenberg@mastodon.social

I have tried the first few steps of the prompts in this article.

I can confirm that GPT can define a language along with conjugations and do basic translations applying the words and rules that are set out.

Ok, wow.

RT @mengk20@twitter.com

How & where do large language models (LLMs) like GPT store knowledge? Can we surgically write *new* facts into them, just like we write records into databases?

Explainer 🧵 on how interpretability & model editing go hand-in-hand, and why these emerging areas are so important 👇

🐦🔗: https://twitter.com/mengk20/status/1588581237345595394

I have put together a curated list of about 50 papers that (IMO) were seminal in defining what "Deep Learning" is today, to share with my students. Goes from 1943-2022.

https://papers.baulab.info/00_README.html

Question for the AI fediverse: What is missing off this list that should be on it?

RT @mengk20@twitter.com

How & where do large language models (LLMs) like GPT store knowledge? Can we surgically write *new* facts into them, just like we write records into databases?

Explainer 🧵 on how interpretability & model editing go hand-in-hand, and why these emerging areas are so important 👇

🐦🔗: https://twitter.com/mengk20/status/1588581237345595394

Multiple openings for both tenure-track and teaching faculty at Northeastern in Computer Science (Boston as well as London, Bay Area, other locations). I am finding it is a great place to be new faculty (ask me). #jobs #teaching

https://www.khoury.northeastern.edu/information-for-overview/prospective-faculty/open-positions/tenure-track/

https://www.khoury.northeastern.edu/information-for-overview/prospective-faculty/open-positions/teaching-faculty/

OK, I get it now: the "Federated" feed shows all posts that people on my local server follow

https://techcrunch.com/2022/11/08/what-is-mastodon/#:~:text=that%20people%20in%20your%20server%20follow

I am switching to sigmoid.social. The federated feed here is way more interesting to me than my original random server.