Nikos Stylianou

155 Followers
283 Following
119 Posts

ML & NLP Researcher

Research Fellow @ITI-CERTH
Adjunct Lecturer @AUTh.gr

Webhttps://nstylia.github.io/
Twitterhttps://twitter.com/nstylia

We have a Lecturer/Reader (Asst/Assoc Prof US) position in #ML at @InfAtEd
!

Join us in #Edinburgh to do world leading research in #ML as well as foundational #AI, #CS and #NLP.

πŸ‘‰https://edin.ac/3XjVfmK
πŸ—“οΈ End 10 Jan 23
πŸ’¬ Chris Williams, Amos Storkey and myself

The city of #Edinburgh is one of the best places to live in the world!

Happy to chat at #NeurIPS2022 with anyone interested!

Pls Share!

Lecturer or Reader in Machine Learning

Applications are invited for an academic position in machine learning in the School of Informatics at the University of Edinburgh, as part of a continuing expansion in Machine Learning and Artificial Intelligence.

University of Edinburgh Jobs
Neural algorithm synthesis is done by giving models a human-crafted programming language and millions of sample programs. Recently, my lab looked at whether neural networks can synthesize algorithms on their own without these crutches. They can, with the right architecture. 🧡

I'm curious, is there a website that has all upcoming (announced at least) conference deadlines?

I used to actively look them up and put them in a spreadsheet but it feels like a colossal waste of time...

#MachineLearning #NLPRoc

New paper 🚨 https://arxiv.org/abs/2211.09260

Can we train a single search system that satisfies our diverse information needs?

We present 𝕋𝔸ℝ𝕋 πŸ₯§ the first multi-task instruction-following retriever trained on 𝔹𝔼ℝℝ𝕀 🫐, a collections of 40 retrieval tasks with instructions! 1/N

#PaperThread #newpaper

Task-aware Retrieval with Instructions

We study the problem of retrieval with instructions, where users of a retrieval system explicitly describe their intent along with their queries, making the system task-aware. We aim to develop a general-purpose task-aware retrieval systems using multi-task instruction tuning that can follow human-written instructions to find the best documents for a given query. To this end, we introduce the first large-scale collection of approximately 40 retrieval datasets with instructions, and present TART, a multi-task retrieval system trained on the diverse retrieval tasks with instructions. TART shows strong capabilities to adapt to a new task via instructions and advances the state of the art on two zero-shot retrieval benchmarks, BEIR and LOTTE, outperforming models up to three times larger. We further introduce a new evaluation setup to better reflect real-world scenarios, pooling diverse documents and tasks. In this setup, TART significantly outperforms competitive baselines, further demonstrating the effectiveness of guiding retrieval with instructions.

arXiv.org

RT @[email protected]

I am delighted to announce that I will be joining UW @[email protected] as an assistant professor starting next year! If you're interested in joining my lab, please consider applying to UW and mentioning me in your application. For more on my research agenda, see https://natashajaques.ai/

πŸ¦πŸ”—: https://twitter.com/natashajaques/status/1593730193008517120

Natasha Jaques

Natasha Jaques

It's the "applications!" time of the year, so let me link to these insightful and oh-so-helpful (and witty) slides by Rocco Servedio on how to write a research statement academic positions and postdocs, from the 2021 Learning Theory Alliance mentoring workshop:
https://let-all.com/assets/slides/How-to-COLT-Rocco.pdf

Lots of good stuff, meaningful advice, and Herman Melville.
#academia #academicjobmarket #researchstatement #hermanmelville

I hate how Google research teams keep pushing for JAX because it reminds me that I have another thing to do over the weekend...

Took a couple of days of social media to focus on work and apparently that's all it took for Twitter to be on the literal brink of collapse.

Nice.

It feels good finishing all reviews in time! Or maybe it's all that caffeine 

One would hope that after Kanye's demise, people would understand that not all publicity is good publicity. Apparently that doesn't include Elon...

Being "all the news" because of the various newly created issues with your platform is not a good thing for a company that aspires to sell ads and needs an immediate boost of revenue.