Sign in

André Martins

@andre-t-martins.bsky.social
83 followers 11 following 9 posts

NLP/ML researcher in Lisbon

PostsRepliesMedia
Reposted by André Martins
Sardine Lab @sardine-lab-it.bsky.social · 28/02/2025
Applications for the 2025 Lisbon Machine Learning Summer School (LxMLS) are open, with @andre-t-martins.bsky.social as one of the organizers. LxMLS is a great opportunity to learn from top speakers and to interact with other students. You can apply for a scholarship. Apply here: lxmls.it.pt/2025/
lxmls.it.pt
LxMLS 2025 - The 15th Lisbon Machine Learning Summer School
021
André Martins @andre-t-martins.bsky.social · 09/03/2025
Our upcoming #AISTATS2025 paper is out: “Sparse Activations as Conformal Predictors” with Margarida Campos, João Calém, Sophia Sklaviadis, and @marfig.bsky.social: arxiv.org/abs/2502.14773. This paper puts together two lines of research, dynamic sparsity and conformal prediction. 🧵
132
Reposted by André Martins
Mário Figueiredo @marfig.bsky.social · 26/02/2025
@andre-t-martins.bsky.social talking about multilingual LLMs at the @priberam.bsky.social Machine Learning Lunch Seminar in @istecnico.bsky.social, @ellisunitlisbon.bsky.social
051
Reposted by André Martins
Sardine Lab @sardine-lab-it.bsky.social · 03/02/2025
🎉 New paper by Saul Santos in collaboration with @tozefarinhas.bsky.social and @andre-t-martins.bsky.social!! 🎉 ∞-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation Paper: arxiv.org/abs/2501.19098
arxiv.org
$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
Current video-language models struggle with long-video understanding due to limited context lengths and reliance on sparse frame subsampling, often leading to information loss. This paper introduces $...
092