TU Ruibo

46 posts

TU Ruibo banner
TU Ruibo

TU Ruibo

@RuiboTu

Ph.D. @KTHuniversity. Work on causality and machine learning.

Stockholm, Sweden Katılım Ekim 2016
326 Takip Edilen95 Takipçiler
TU Ruibo
TU Ruibo@RuiboTu·
5 years! You made it! An excellent research story!
yingzhen@liyzhen2

This paper took @BalsellsRodas ~5 years in making: 2020/21: MSc proj, toy exp🐣 2022: added more exp, rejected due to weak theory 😥 2023/24: invented a new proof tech in another proj 🤔 2024/25: revisit, apply new proof tech, resubmit -> accepted 🥳 Persistence pays off indeed👍

English
0
0
1
55
TU Ruibo retweetledi
yingzhen
yingzhen@liyzhen2·
This paper took @BalsellsRodas ~5 years in making: 2020/21: MSc proj, toy exp🐣 2022: added more exp, rejected due to weak theory 😥 2023/24: invented a new proof tech in another proj 🤔 2024/25: revisit, apply new proof tech, resubmit -> accepted 🥳 Persistence pays off indeed👍
Carles Balsells Rodas@BalsellsRodas

Excited to share that our paper "Causal discovery from Conditionally Stationary Time Series" has been accepted to ICML 2025!🥳 Pre-print: arxiv.org/abs/2110.06257 Thank you very much to all my collaborators, persistence pays off! #icml #icml2025

English
1
2
43
3.3K
TU Ruibo retweetledi
Kevin Patrick Murphy
Kevin Patrick Murphy@sirbayes·
I am pleased to announce that I have updated the online versions of my 2 textbooks (see probml.github.io/pml-book/): I fixed all issues listed on github, added some new references (esp on LLMs), and made a few other small tweaks.
English
15
166
1.3K
68.3K
TU Ruibo
TU Ruibo@RuiboTu·
3. ChatGPT can give some correct non-trivial answers serving as a good complementary for causal discovery methods. This might open up new research opportunities on utilizing the large language models to complement, improve and develop better causal machine learning tools.
English
0
0
0
107
TU Ruibo
TU Ruibo@RuiboTu·
2. We need to be extremely cautious about using causal claims made by ChatGPT as causal discovery results. This is because causal discovery and causal question answering with large language models are fundamentally different tasks.
English
1
0
0
121
TU Ruibo
TU Ruibo@RuiboTu·
Are you curious about the performance of #ChatGPT on #CausalDiscovery? We do. So we push its limit and explore its ability to answer causal discovery questions by using a causal medical benchmark. The full report serves as an appendix to the benchmark 👇 shorturl.at/bGH45
English
1
2
10
873
Jean-François Ton
Jean-François Ton@jeanfrancois287·
Happy to announce that I have joined @BytedanceTalk as a Senior Research Scientist working in the Machine Learning Fairness team in London 🎊🎉 I will be working on Causal Inference and XAI here. Come say hi if you are based in London!
English
10
0
96
0
TU Ruibo retweetledi
Bill Gates
Bill Gates@BillGates·
The brilliant team behind the Oceanbird is reducing carbon emissions in the sailing industry by up to 90% using clean wind power technology.
English
0
115
844
0
TU Ruibo retweetledi
Amazon Science
Amazon Science@AmazonScience·
Announced today, @awscloud and @MSFTResearch partnered to create a new @GitHub organization called PyWhy—where novel causal-analysis algorithms developed by Amazon will augment DoWhy, Microsoft's existing causality library. #AmazonScience #AWS
English
5
31
121
0
Sara Magliacane hiring PhDs at UvA
Sara Magliacane hiring PhDs at UvA@saramagliacane·
All models except one are "wrong" (i.e. not #causal), but some are useful? Come join us to #CRL22 at @UncertaintyInAI in August in Eindhoven 🇳🇱 to learn more #whatIsIdentifiability #causality #causalTwitter #representationLearning
Causal Representation Learning Workshop @ UAI'22@crl_uai

Announcing the 1st Workshop on Causal Representation Learning (CRL) at UAI'22 (@UncertaintyInAI). When? - 5 August 2022 Where? - Eindhoven, The Netherlands Format? - Hybrid Call for papers, program & other details: crl-uai-2022.github.io Please consider submitting your work!

English
1
9
39
0
Open Review
Open Review@openreviewnet·
OpenReview just smoothly weathered the #NeurIPS2021 deadline today, hardly breaking a sweat. Over 41k sessions, 35k active users (29k in final 2 hours), more PDFs submitted than we’re allowed to say, sub-second response time on most requests, CPU utilization never surpassing 15%.
English
11
75
840
0
TU Ruibo
TU Ruibo@RuiboTu·
@rasbt Thank you so much for your suggestion. This sounds an excellent way to organize knowledge ! This will be certainly my first flag in my 2021 list. Great thanks!
English
0
0
0
0
Sebastian Raschka
Sebastian Raschka@rasbt·
Useful tips not only for those doing a PhD but researchers in machine learning in general: 1) Have a number of go-to links to find references to related papers 2) Keep a reading list of papers 3) Have a paper reading strategy 4) Occasionally read up on different areas 1/3
Maithra Raghu@maithra_raghu

New blog post: "Reflections on my (Machine Learning) PhD Journey" maithraraghu.com/blog/2020/Refl… 2020 has marked the end of my six year PhD journey, filled with struggles, success and evolution of personal & research perspectives. In the post I share experiences and lessons learned ⬇️

English
6
66
292
0
TU Ruibo
TU Ruibo@RuiboTu·
(5/5) A: Not say assumptions doesn’t mean general. There are implicit assumptions of intuitions. If only rely on intuitions without further specifying and understanding underlying assumptions, this would be the most we would achieve, which would be a pity for it and the field.
English
0
0
0
0
TU Ruibo
TU Ruibo@RuiboTu·
(4/5) A: For sure, the method in XXX paper captures very important intuitions making its performance excellent, which is great for the field. But the generalisation without specifying how it generalises and how general it can be could be vague and misleading as well.
English
1
0
0
0
TU Ruibo
TU Ruibo@RuiboTu·
(1/5) In our machine learning reading group at KTH, we had a very insightful discussion. It is about transfer learning, that is the generalisation without human involved specification what we want ? In other words, is the human involved specification what we don’t want?
English
1
1
0
0

Keşfet

@BalsellsRodas @jeanfrancois287 @BytedanceTalk @awscloud @MSFTResearch @github @saramagliacane @UncertaintyInAI