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 (Mar 27 - April 2)

elvis
Apr 2, 2023
14
Share this post

🥇Top ML Papers of the Week

nlp.elvissaravia.com
Share

1). BloombergGPT - a new 50B parameter large language model for finance. Claims the largest domain-specific dataset yet with 363 billion tokens... further augmented with 345 billion tokens from general-purpose datasets; outperforms existing models on financial tasks while not sacrificing performance on general LLM benchmarks. (paper)

Twitter avatar for @omarsar0
elvis @omarsar0
BloombergGPT is a new LLM for finance. It's a 50 billion parameter language model trained on financial data. Claims the largest domain-specific dataset yet with 363 billion tokens... further augmented with 345 billion tokens from general purpose arxiv.org/abs/2303.17564…… https://t.co/s6AfoEPWCx
Image
1:00 PM ∙ Mar 31, 2023
3,691Likes699Retweets

2). ALOHA - a low-cost system that performs end-to-end imitation learning from real demonstrations; also presents an algorithm called Action Chunking with Transformers to learn a generative model that allows a robot to learn difficult tasks in the real world. (paper | code)

Twitter avatar for @tonyzzhao
Tony Z. Zhao @tonyzzhao
Introducing ALOHA 🏖: 𝐀 𝐋ow-cost 𝐎pen-source 𝐇𝐀rdware System for Bimanual Teleoperation After 8 months iterating @Stanford and 2 months working with beta users, we are finally ready to release it! Here is what ALOHA is capable of:
4:39 PM ∙ Mar 27, 2023
2,772Likes634Retweets

3). HuggingGPT - a system that leverages LLMs like ChatGPT to conduct task planning, select models and act as a controller to execute subtasks and summarize responses according to execution results. (paper)

Twitter avatar for @johnjnay
John Nay @johnjnay
HuggingGPT -Human requests something -ChatGPT 1 Plans tasks 2 Selects AI models based on HuggingFace descriptions 3 Manages cooperation of expert models to execute subtasks 4 Summarizes results Covers many sophisticated tasks across modalities & domains arxiv.org/abs/2303.17580
Image
1:13 AM ∙ Mar 31, 2023
2,427Likes445Retweets

4). ChatDoctor - a medical chat model fine-tuned on LLaMA using medical domain knowledge. Collects data on around 700 diseases and generated 5K doctor-patient conversations to finetune the LLM. (paper | code)

Twitter avatar for @omarsar0
elvis @omarsar0
ChatDoctor: A medical chat model fine-tuned on LLaMA using medical domain knowledge. Collects data on around 700 diseases and generated 5K doctor-patient conversations to finetune the LLM. paper: arxiv.org/abs/2303.14070 code: github.com/Kent0n-Li/Chat… https://t.co/PdBl3fiijv
Image
1:24 AM ∙ Mar 28, 2023
1,652Likes401Retweets

5). LLaMA-Adapter - a lightweight adaption method to efficiently fine-tune LLaMA into an instruction-following model; generates responses comparable to Alpaca with fully fine-tuned 7B parameter; it’s also extended for multi-modal input support. (paper | code)

Twitter avatar for @rasbt
Sebastian Raschka @rasbt
LLaMA-Adapter: finetuning large language models (LLMs) like LLaMA and matching Alpaca's modeling performance with greater finetuning efficiency Let's have a look at this new paper (arxiv.org/abs/2303.16199) that proposes an adapter method for LLaMA instruction finetuning 1/5
Image
3:09 PM ∙ Mar 30, 2023
966Likes175Retweets

6). ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks - demonstrates that ChatGPT can outperform crowd-workers for several annotation tasks such as relevance, topics, and frames detection; besides better zero-shot accuracy, the per-annotation cost of ChatGPT is less 20 times cheaper than MTurk. (paper)

Twitter avatar for @AlphaSignalAI
Lior⚡ @AlphaSignalAI
This is big news, ChatGPT just outperformed mechanical turk workers on text annotation tasks! We're getting closer to complete AI-based data annotation, which in turn, can be used to train AI models. It will cause a big shift in the industry. Paper: arxiv.org/pdf/2303.15056…
Image
5:45 PM ∙ Mar 30, 2023
1,877Likes423Retweets

7). LLMs for Computer Tasks - shows that a pre-trained LLM agent can execute computer tasks using a simple prompting scheme where the agent recursively criticizes and improves its outputs. (paper)

Twitter avatar for @arankomatsuzaki
Aran Komatsuzaki @arankomatsuzaki
Language Models can Solve Computer Tasks Letting LLM to recursively criticize and improve its output significantly outperforms existing LLM methods on computer tasks and surpasses supervised learning (SL) and RL approaches. arxiv.org/abs/2303.17491
Image
1:13 AM ∙ Mar 31, 2023
459Likes92Retweets

8). Dialog-Enabled Resolving Agents (DERA) - a paradigm to enhance large language model completions by allowing models to communicate feedback and iteratively improve output; DERA outperforms base GPT-4 on clinically-focused tasks. (paper)

Twitter avatar for @johnjnay
John Nay @johnjnay
Forums for LLM Agents to Communicate Can Improve Outputs 1) Human provides task 2) "Decider" Agent produces output 3) "Researcher" & Decider Agents discuss 4) Decider decides Big improvement over base GPT4 on medical summarization & care plan generation arxiv.org/abs/2303.17071
Image
2:15 PM ∙ Apr 1, 2023
856Likes146Retweets

9). Natural Selection Favors AIs over Humans - discusses why AI systems will become more fit than humans and the potential dangers and risks involved, including ways to mitigate them. (paper)

Twitter avatar for @DanHendrycks
Dan Hendrycks @DanHendrycks
As AI systems become more useful, people will delegate greater authority to them across more tasks. AIs are evolving in an increasingly frenzied and uncontrolled manner. This carries risks as natural selection favors AIs over humans. Paper: arxiv.org/abs/2303.16200 (🧵 below)
 Forces that fuel selfishness and erode safety.
Darwinism and evolution apply to more than just biological organisms and generalized across different domains.
3:38 PM ∙ Mar 29, 2023
175Likes30Retweets

10). ML for Partial Differential Equations - a review examining avenues of partial differential equations research advanced by machine learning. (paper)

Twitter avatar for @DynamicsSIAM
DynamicalSystemsSIAM @DynamicsSIAM
"Machine Learning for Partial Differential Equations" (by Steven L. Brunton, J. Nathan Kutz): arxiv.org/abs/2303.17078
1:07 AM ∙ Mar 31, 2023
616Likes129Retweets

14
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