English
English Indonesia Türkçe Deutsch Español Português Pусский Français Italiano Nederlands Polski العربية ไทย Tiếng Việt 繁體中文 简体中文 日本語 한국어
lorebasile's profile picture. Postdoc @AreaSciencePark

Lorenzo Basile

@lorebasile

Postdoc @AreaSciencePark

6Posts 37Followers 265Following
You might like
Lorenzo Basile reposted
AreaSciencePark's profile picture.
Area Science Park
 @AreaSciencePark
Nov 20

🤖Seminar Series Next week, Giorgos Nikolaou and Tommaso Mencattini (@EPFL) will present "Language Models are Injective and Hence Invertible". @GiorgosNik02 @tommaso_mncttn 📅Nov 27, 11 CET (Online) 👉Register to attend: bit.ly/4ieKRYq

AreaSciencePark's tweet image. 🤖Seminar Series Next week, Giorgos Nikolaou and Tommaso Mencattini (@EPFL) will present "Language Models are Injective and Hence Invertible". @GiorgosNik02 @tommaso_mncttn 📅Nov 27, 11 CET (Online) 👉Register to attend: bit.ly/4ieKRYq
0
6
10
0
563
Lorenzo Basile reposted
albecazzaniga's profile picture.
Alberto Cazzaniga
 @albecazzaniga
Sep 22

Excited to share that 2/2 papers from our Lab (LADE) were accepted to #NeurIPS2025 (one spotlight 🎉) Great work from all the students and collaborators involved! @AreaSciencePark @aleserra1998 @lorebasile @francescortu @lucrevaleriani @DiegoDoimo @ansuin @FrancescoLocat8

albecazzaniga's tweet image. Excited to share that 2/2 papers from our Lab (LADE) were accepted to #NeurIPS2025 (one spotlight 🎉) Great work from all the students and collaborators involved! @AreaSciencePark @aleserra1998 @lorebasile @francescortu @lucrevaleriani @DiegoDoimo @ansuin @FrancescoLocat8
1
8
19
5
2K
Lorenzo Basile reposted
francescortu's profile picture.
francesco ortu
 @francescortu
Sep 19

Thrilled to announce that our paper is accepted at #NeurIPS 2025!! See you in San Diego! 🇺🇸

francescortu's profile picture. NLP & Interpretability | PhD Student @UniTrieste & Data Engineering Lab @AreaSciencePark | Prev @MPI_IS intern https://t.co/RM03tgnbJP
francesco ortu
 @francescortu
Dec 10

🚨🚨 Excited to share our latest paper, now on @arxiv! 🖼️ We studied how unified VLMs, trained to generate both text and images (e.g., @MetaAI's Chameleon), exchange information between modalities, comparing them to standard VLMs. Deep dive:👇

francescortu's tweet image. 🚨🚨 Excited to share our latest paper, now on @arxiv! 🖼️ We studied how unified VLMs, trained to generate both text and images (e.g., @MetaAI's Chameleon), exchange information between modalities, comparing them to standard VLMs. Deep dive:👇
1
4
15
6
2K
1
2
5
0
351
Lorenzo Basile reposted
francescortu's profile picture.
francesco ortu
 @francescortu
Dec 10

🚨🚨 Excited to share our latest paper, now on @arxiv! 🖼️ We studied how unified VLMs, trained to generate both text and images (e.g., @MetaAI's Chameleon), exchange information between modalities, comparing them to standard VLMs. Deep dive:👇

francescortu's tweet image. 🚨🚨 Excited to share our latest paper, now on @arxiv! 🖼️ We studied how unified VLMs, trained to generate both text and images (e.g., @MetaAI's Chameleon), exchange information between modalities, comparing them to standard VLMs. Deep dive:👇
1
4
15
6
2K
Lorenzo Basile reposted
DiegoDoimo's profile picture.
Diego
 @DiegoDoimo
Dec 10

I just landed in Vancouver to present @NeurIPSConf the findings of our new work! Few-shot learning and fine-tuning change the hidden layers of LLMs in a dramatically different way, even when they perform equally well on multiple-choice question-answering tasks. 🧵1/6

DiegoDoimo's tweet image. I just landed in Vancouver to present @NeurIPSConf the findings of our new work! Few-shot learning and fine-tuning change the hidden layers of LLMs in a dramatically different way, even when they perform equally well on multiple-choice question-answering tasks. 🧵1/6
1
5
17
5
1K
Lorenzo Basile reposted
ValeMaiorca's profile picture.
Valentino Maiorca
 @ValeMaiorca
Nov 4, 2024

✨ Meet #ResiDual, a novel perspective on the alignment of multimodal latent spaces! Think of it as a spectral "panning for gold" along the residual stream. It improves text-image alignment by simply amplifying task-related directions! 🌌🔍 arxiv.org/abs/2411.00246 [1/6]

ValeMaiorca's tweet image. ✨ Meet #ResiDual, a novel perspective on the alignment of multimodal latent spaces! Think of it as a spectral "panning for gold" along the residual stream. It improves text-image alignment by simply amplifying task-related directions! 🌌🔍 arxiv.org/abs/2411.00246 [1/6]
2
11
29
5
3K

United States Trends

You might like

Something went wrong.


Something went wrong.