NLP Newsletter

Share this post

🥇Top ML Papers of the Week

nlp.elvissaravia.com

Discover more from NLP Newsletter

The NLP newsletter covers the latest trending natural language processing (NLP) and machine learning (ML) news, projects, resources, and research papers.
Over 10,000 subscribers
Continue reading
Sign in

🥇Top ML Papers of the Week

The top ML Papers of the Week (Jan 23-29)

elvis
Jan 29, 2023
8
Share this post

🥇Top ML Papers of the Week

nlp.elvissaravia.com
Share

In this edition of the NLP Newsletter, we cover the top ML Papers of the Week (Jan 23-29).


1) MusicLM - a generative model for generating high-fidelity music from text descriptions. (Paper | Tweet)

Twitter avatar for @_akhaliq
AK @_akhaliq
MusicLM: Generating Music From Text abs: arxiv.org/abs/2301.11325 project page: google-research.github.io/seanet/musiclm…
1:56 AM ∙ Jan 27, 2023
1,479Likes342Retweets

2) H3 - an approach to reduce the gap, in terms of performance and hardware utilization, between state space models and attention for language modeling. (Paper | Tweet)

Twitter avatar for @realDanFu
Dan Fu @realDanFu
Attention is all you need... but how much of it do you need? Announcing H3 - a new generative language models that outperforms GPT-Neo-2.7B with only *2* attention layers! Accepted as a *spotlight* at #ICLR2023! 📣 w/ @tri_dao 📜 arxiv.org/abs/2212.14052 1/n
7:31 PM ∙ Jan 23, 2023
1,540Likes247Retweets

3) A Watermark for LLMs - a watermarking framework for proprietary language models. (Paper | Tweet)

Twitter avatar for @tomgoldsteincs
Tom Goldstein @tomgoldsteincs
#OpenAI is planning to stop #ChatGPT users from making social media bots and cheating on homework by "watermarking" outputs. How well could this really work? Here's just 23 words from a 1.3B parameter watermarked LLM. We detected it with 99.999999999994% confidence. Here's how 🧵
Image
4:40 PM ∙ Jan 25, 2023
4,520Likes972Retweets

4) Make-A-Video3D - a new text-to-4D model for dynamic scene generation from input text. (Paper | Tweet | Project)

Twitter avatar for @deviparikh
Devi Parikh @deviparikh
Introducing Make-A-Video3D! Generating 3D dynamic (mini) scenes from input text. That is, text --> 4D! Needs no 4D data (i.e., no dynamic 3D data), no static 3D data, no paired text-video data. Paper: arxiv.org/abs/2301.11280 Website: make-a-video3d.github.io
6:57 PM ∙ Jan 27, 2023
1,318Likes259Retweets

5). ClimaX - a foundation model for weather and climate, including many capabilities for atmospheric science tasks. (Paper | Tweet | Blog)

Twitter avatar for @tungnd_13
Tung Nguyen @tungnd_13
Introducing ClimaX, the first foundation model for weather and climate. A fast and accurate one-stop AI solution for a range of atmospheric science tasks. Paper: arxiv.org/abs/2301.10343 Blog: microsoft.com/en-us/research… Thread🧵 #ML #Climate #Weather #FoundationModel
Image
4:10 PM ∙ Jan 26, 2023
714Likes151Retweets

6) Open Problems in Applied Deep Learning - a new reference to learn about interesting open problems in deep learning. (Paper | Tweet)

Twitter avatar for @omarsar0
elvis @omarsar0
Open Problems in Applied Deep Learning If you're looking for interesting open problems in DL, this is a good reference. Not sure if intentional but it also looks useful to get a general picture of current trends in deep learning with ~300 references. arxiv.org/abs/2301.11316 https://t.co/XGqIo9Hjnk
Image
3:32 PM ∙ Jan 27, 2023
989Likes232Retweets

7) DetectGPT - an approach for zero-shot machine-generated text detection. Uses raw log probabilities from the LLM to determine if the passage was sampled from it. (Paper | Tweet)

Twitter avatar for @chelseabfinn
Chelsea Finn @chelseabfinn
LLMs like ChatGPT are becoming more fluent – how can we detect if something was written by a language model or a human? We developed DetectGPT: a method for detecting if a passage was written by a particular language model.
Visualization showing a candidate passage going into DetectGPT, where DetectGPT then predicts whether the passage is from a model or another source.
4:06 AM ∙ Jan 27, 2023
1,017Likes205Retweets

8) StyleGAN-T - a new model that aims to regain competitiveness of GANs for fast large scale text-to-image synthesis. (Paper | Tweet)

Twitter avatar for @_akhaliq
AK @_akhaliq
StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis significantly improves over previous GANs and outperforms distilled diffusion models in terms of sample quality and speed abs: arxiv.org/abs/2301.09515 project page: sites.google.com/view/stylegan-…
1:58 AM ∙ Jan 24, 2023
862Likes181Retweets

9) ProGen - an LLM that can generate protein sequences with a predictable function across large protein families. (Paper | Tweet)

Twitter avatar for @nikhil_ai
Nikhil Naik @nikhil_ai
Excited to have our paper on using large language models like ChatGPT for protein design come out in @NatureBiotech! You can tell a language model which type of protein to design, and it can generate one from scratch!
nature.comLarge language models generate functional protein sequences across diverse families - Nature BiotechnologyA generative deep-learning model designs artificial proteins with desired enzymatic activities.
5:45 PM ∙ Jan 26, 2023
878Likes199Retweets

10) The Impossibility of Parallelizing Boosting - investigates the possibility of parallelizing boosting. (Paper | Tweet)

Twitter avatar for @aminkarbasi
Amin Karbasi @aminkarbasi
Well, it turned out we cannot parallelize boosting!!! arxiv.org/abs/2301.09627
Image
4:22 AM ∙ Jan 28, 2023
655Likes69Retweets
8
Share this post

🥇Top ML Papers of the Week

nlp.elvissaravia.com
Share
Comments
Top
New
Community

No posts

Ready for more?

© 2023 elvis
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing