Carles Balsells Rodas
@BalsellsRodas
Followers
56
Following
207
Media
0
Statuses
44
Joined October 2022
If you are attending ICML 2025 and interested in Causal Discovery, I will be presenting our work today at 11am! See you at the East Exibition Hall - Poster 1303. #icml #icml2025
Excited to share that our paper "Causal discovery from Conditionally Stationary Time Series" has been accepted to ICML 2025!🥳 Pre-print: https://t.co/tPlw7p5Ja4 Thank you very much to all my collaborators, persistence pays off! #icml #icml2025
0
1
9
RT @jacobyhsi88: VUD’s gonna be at #NeurIPS2025 🎉🥳
0
1
0
Wanna understand the sources of uncertainty in LLMs when performing in-context learning 🤔? 🚀 We introduce a variational uncertainty decomposition framework for in-context learning without explicitly sampling from the latent parameter posterior. 📄 Paper:
We show how to make LLM in-context learning approximately Bayesian & decompose uncertainty IMO this is proper approximate inference 🥰 applied to LLMs Led by awesome students @shavindra_j @jacobyhsi88 Filippo & Wenlong 👍 Example👇by prompting, bandits & NLP examples in paper
2
7
23
#AISTATS2026 call for papers is out! We welcome solid Stats and AI/ML work from you 🤗 (2026 conference will have further exciting initiatives, watch this space 😇
📣 Please share: We invite submissions to the 29th International Conference on Artificial Intelligence and Statistics (#AISTATS2026) and welcome paper submissions at the intersection of AI, machine learning, statistics, and related areas. @aistats_conf [1/3]
0
1
15
long overdue, but we finally have a team photo! 😊 (some of them also on this site @JzinOu @jacobyhsi88 @BalsellsRodas
0
3
31
Excited to share that our paper "Causal discovery from Conditionally Stationary Time Series" has been accepted to ICML 2025!🥳 Pre-print: https://t.co/tPlw7p5Ja4 Thank you very much to all my collaborators, persistence pays off! #icml #icml2025
arxiv.org
Causal discovery, i.e., inferring underlying causal relationships from observational data, is highly challenging for AI systems. In a time series modeling context, traditional causal discovery...
1
7
28
Gonna present 3 papers at #ICLR2025 and #AABI, come and connect at👇 1. Oral session 1c on FIRST DAY Morning: Improving Diffusion Model with Optimal Diagonal Covariance Matching ( https://t.co/YjcGro9GR1)
2
4
21
check our ICLR'25 oral paper if you are interested:
arxiv.org
The probabilistic diffusion model has become highly effective across various domains. Typically, sampling from a diffusion model involves using a denoising distribution characterized by a Gaussian...
The next seminar is this Friday (April 4th) and starts at 12pm midday UK time! @JzinOu from @imperialcollege is going to talk about “Diffusion models beyond mean prediction”! https://t.co/WIZ32HhI2G This seminar is hybrid. More info 👉 https://t.co/9pUy2RWAy1
0
7
20
Is there an elementary way to understand matrix/tensor factorization, and their algebraic connection with transformer models?🤔 Our answer is YES! All you need is undergraduate-level linear algebra, and a little geometry intuition! https://t.co/BSbxJSef2l.
#geometry #tensor 1/7
arxiv.org
Matrix and tensor-guided parametrization for Natural Language Processing (NLP) models is fundamentally useful for the improvement of the model's systematic efficiency. However, the internal links...
2
5
15
📢Submit by Nov 2 to CLeaR, if you are researching on Causal Discovery, Causal Inference, Intersections of Causality and Machine Learning, and many others! Check out our Call for Papers https://t.co/eyzQQsBopt
We are thrilled to announce the 4th Conference on Causal Learning and Reasoning (CLeaR), taking place in Lausanne, Switzerland, from May 7-9, 2025! Submission deadline: Nov 2, 2024, 11:59 PM AoE. For details, visit https://t.co/eyzQQsBopt 😀😎
0
12
33
I enjoyed my time presenting our poster at #ICML2024! Special thanks to the people who stopped by and my collaborators once again! @wendy_yusi @coopermj_aiml @rahulgk
[ICML 2024 (Spotlight)] How can we distill predictive signals from tabular data to obtain intelligible insights 🤔? We introduce InterpreTabNet, a variant of the TabNet model that leverages salient feature interpretation. 📄: https://t.co/WDXKDjsKSs 💻:
6
2
12
I’ll be presenting our #ICML2024 Spotlight paper on interpretable tabular learning this Wednesday, 11am, at Hall C 4-9, Poster #508 🇦🇹! Come check us out 🙌! Work done with @wendy_yusi, @coopermj_aiml, and @rahulgk at @VectorInst/@UofTCompSci 🇨🇦.
5
5
8
[ICML 2024 (Spotlight)] How can we distill predictive signals from tabular data to obtain intelligible insights 🤔? We introduce InterpreTabNet, a variant of the TabNet model that leverages salient feature interpretation. 📄: https://t.co/WDXKDjsKSs 💻:
1
3
14
🚨 Want to join us? - We offer 5 postdoc positions in European projects in València - ML/DL, #Earth science, #hybrid modelling, #climate model #parametrization, #UQ, #diffusion & #foundation models - Apply by Aug 1st 2024: https://t.co/hnAtT8q4L7 Happy summer! 🌊🌞🥘⚽️
2
28
36
Excited to share that our paper, "Identifiability of Total Effects from Abstractions of Time Series Causal Graphs," has been accepted to @UncertaintyInAI! 🎉 If you're attending #UAI2024, stop by my poster tomorrow. Can't make it? Check it out online:
0
3
17
RT-LA-VocE has been accepted at #INTERSPEECH2024 ! 🥳 https://t.co/o06VFoNCOf Our new model builds on top of the original LA-VocE (ICASSP 2023) to enable real-time⌛️ audio🔊-visual👀 speech💬 enhancement🔨 in real-world video streaming applications. Details below :) 🧵[1/9]
1
3
11
Identifying Nonstationary Causal Structures with High-Order Markov Switching Models.
arxiv.org
Causal discovery in time series is a rapidly evolving field with a wide variety of applications in other areas such as climate science and neuroscience. Traditional approaches assume a stationary...
0
2
4
We start the 4th day of #GeMSS ( https://t.co/Z2MzoBqXan) a.k.a. the best #GenAI summer school in the world! We begin with amazing @liyzhen2 and sequential deep generative modeling ✨
1
6
31
We are THRILLED to have been ranked 2nd in the world and 1st in the UK and Europe in this year's QS @worlduniranking! 🎊🥳 #QSWUR Thank you to everyone in #OurImperial community for making this result possible! 💙
37
414
1K
🎉Happy to share that our paper “On the Identifiability of Switching Dynamical Systems” has been accepted to ICML! Preprint: https://t.co/ZK1V0uTNTr
@yixinwang_ @liyzhen2
arxiv.org
The identifiability of latent variable models has received increasing attention due to its relevance in interpretability and out-of-distribution generalisation. In this work, we study the...
3
6
24