Michelle Yuan
@michyuan
Followers
488
Following
490
Media
11
Statuses
99
Principal Applied Scientist @oracle doing NLP/ML/AI research.
Antarctica
Joined May 2018
RT @ChengleiSi: Automating AI research is exciting! But can LLMs actually produce novel, expert-level research ideas?. After a year-long st….
0
770
0
RT @debarghya_das: Stories have 6 primary arcs:. • “Rags to riches” (rise).• “Tragedy” (fall).• “Man in a hole” (fall-rise).• “Icarus” (ris….
0
412
0
RT @h__j___han: Do the best translations go beyond literal meaning?.Excited to share our work at #EMNLP2023 on Automatic Explicitation in t….
0
11
0
RT @adamfungi: This new paper with Santosh Vempala gives a simple statistical justification for why and when Language Models *should* hallu….
arxiv.org
Recent language models generate false but plausible-sounding text with surprising frequency. Such "hallucinations" are an obstacle to the usability of language-based AI systems and can harm people...
0
81
0
RT @srush_nlp: Vector databases have raised billions offering hosted management of text embeddings. What are you revealing in these vectors….
0
91
0
RT @juletxara: Do multilingual language models think better in English? 🤔. Yes, they do! We show that using an LLM to translate its input i….
0
46
0
Check out this large, multilingual dataset with passages from millions of Wikipedia articles and material from their cited sources!.
We want LLMs to write reports, but how can we teach them to find and synthesize info that is multi-doc and across languages? 🤔. Towards this, we mine 13M Wiki pages and their source materials (71M webpages) in 50 langs 🤯.🤗 📝
0
1
12
RT @psanfernandes: *Human feedback* was the necessary secret sauce in making #chatgpt so human-like.But what exactly is feedback? And how c….
0
99
0
RT @aselipsky: We’re announcing Amazon Bedrock—giving customers the easiest way to build and scale generative AI applications with access t….
aws.amazon.com
The seeds of a machine learning (ML) paradigm shift have existed for decades, but with the ready availability of scalable compute capacity, a massive proliferation of data, and the rapid advancement...
0
343
0
RT @samsontmr: 🚨BREAKING NEWS🚨. Looking to work on LLM research this summer?. Our team in @awscloud AI Research and Education has reopened….
0
21
0
RT @arankomatsuzaki: Toolformer: Language Models Can Teach Themselves to Use Tools . Presents Toolformer, a model trained to decide which A….
0
238
0
Really exciting to see transformers being used for earth science!.
Earthformer - a space-time Transformer for Earth system forecasting. Earthformer is based on a generic, flexible and efficient space-time attention block called Cuboid Attention. GitHub: Try it out with Colab: #DeepLearning #python
0
0
6
RT @bleedingedgeai: These are the most impressive chats we've seen with ChatGPT so far. It can. .
0
641
0
RT @ClipUmd: Our researchers won a Best Paper Award @aaclmeeting for their work to make visual question answering (VQA) systems more effect….
0
7
0
Hokkien is the second most popular dialect in Taiwan, one of the most linguistically diverse places in the world. Some say that Taiwan is the “Urheimat” of the Austronesian languages family. Would love to see AI developed to help preserve these beautiful, spoken languages.
(1/3) Until now, AI translation has focused mainly on written languages. Universal Speech Translator (UST) is the 1st AI-powered speech-to-speech translation system for a primarily oral language, translating Hokkien, one of many primarily spoken languages.
0
1
7
RT @ShayneRedford: 📢 A 🧵 on the Trends in NLP Datasets. What’s changed since SQuAD was all the rage in 2016? A: A LOT. 🔭. 1. Generic ➡️ Ni….
0
46
0
RT @wittgen_ball: #NLProc: Stop annotating randomly-sampled data! Select-then-annotate to make language models better few-shot in-context l….
0
65
0