FBK - NLP Research Group
@fbk-nlp.bsky.social
๐ค 129
๐ฅ 206
๐ 19
#NLP
Research Unit at @ Fondazione Bruno Kessler Site:
https://nlplab.fbk.eu
#NLProc
๐ Big news from
#CLiCit2025
! Our PhD student Davide Testa presented MAIA ๐๏ธ๐ง ๐ฎ๐น โ the first Italian benchmark to test Vision-Language Models on multimodal reasoning & robustness. ๐ You can check the Paper in the CLiC-it pre-processing:
clic2025.unica.it/wp-content/u...
#AI
#NLProc
#VLMs
5 months ago
0
1
0
๐Congrats to our PhD student Sofia Brenna for presenting her poster at
#SigDIAL2025
in Avignon ๐ซ๐ท about "Investigating Proactivity in Task-Oriented Dialogues", recently published in Dialogue & Discours journal. Paper here:
journals.uic.edu/ojs/index.ph...
#NLProc
5 months ago
0
2
0
๐ Thrilled to share that our paper โAll-in-one: Understanding and Generation in Multimodal Reasoning with the MAIA Benchmarkโ has been accepted at the EMNLP 2025 conference! ๐ฅ ๐ Preprint here:
arxiv.org/abs/2502.16989
See you in Suzhou next November!!! ๐จ๐ณ๐
#EMNLP2025
#NLP
#Multimodality
loading . . .
All-in-one: Understanding and Generation in Multimodal Reasoning with the MAIA Benchmark
We introduce MAIA (Multimodal AI Assessment), a native-Italian benchmark designed for fine-grained investigation of the reasoning abilities of visual language models on videos. MAIA differs from other...
https://arxiv.org/abs/2502.16989
6 months ago
0
2
2
๐ Can Vision-Language Models plan effectively? We introduce ViPlan, a benchmark comparing: ๐น VLM-as-planner ๐น VLM-as-grounder ๐ Home robotics ๐งฑ Visual Blocksworld Spoiler alert:โ Visual-Reasoning ๐ Pre-print here:
arxiv.org/abs/2505.13180
#VLM
#AI
#NLProc
9 months ago
0
0
0
๐ Exciting News! The Evalita-LLM Leaderboard is now live on Hugging Face! Explore the performance of over 40 Large Language Models on native Italian tasks. Dive in here:
huggingface.co/spaces/evali...
@FondazioneBrunoKessler @igenius
@diunito.bsky.social
#NLProc
#LLM
#AI
#Italian
#Benchmarking
loading . . .
Evalita Llm Leaderboard - a Hugging Face Space by evalitahf
Duplicate this leaderboard to initialize your own!
https://huggingface.co/spaces/evalitahf/evalita_llm_leaderboard
11 months ago
0
0
2
Don't miss out โผ๏ธ Join us at Wired Health 2025
#WH25๐ญ
Our Head Unit, Bernardo Magnini will take the stage to discuss "Artificial Intelligence and Clinical Data: The Future of Emergency Medicine." ๐ฅ Full program here:
lnkd.in/eKi44biT
@wired.com
#AI
#healthcare
#Innovation
11 months ago
0
0
0
Welcome to MAIA! ๐ Our new benchmark for evaluating multimodal reasoning in Vision-LMs on videos fully in Italian! ๐ฎ๐น MAIA tests understanding & generation with fine-grained reasoning categories and a brand-new evaluation metric! ๐๐ฅDiscover MAIA here:
arxiv.org/abs/2502.16989
#NLProc
#evaluation
#AI
loading . . .
All-in-one: Understanding and Generation in Multimodal Reasoning with the MAIA Benchmark
We introduce MAIA (Multimodal AI Assessment), a native-Italian benchmark designed for fine-grained investigation of the reasoning abilities of visual language models on videos. MAIA differs from other...
https://arxiv.org/abs/2502.16989
12 months ago
1
6
3
๐ **Exciting News!** ๐ Evalita-LLM is here! ๐ฎ๐น A new benchmark for evaluating LLMsโoffering native Italian tasks, generative challenges, and fair multi-prompt evaluations. Now also available in lm-evaluation harness by
@eleutherai.bsky.social
! ArXiv:
arxiv.org/abs/2502.02289
#NLProc
#LLM
#Evaluation
loading . . .
Evalita-LLM: Benchmarking Large Language Models on Italian
We describe Evalita-LLM, a new benchmark designed to evaluate Large Language Models (LLMs) on Italian tasks. The distinguishing and innovative features of Evalita-LLM are the following: (i) all tasks ...
https://arxiv.org/abs/2502.02289
12 months ago
0
9
4
Our group leader took the stage at the FBK plenary session to showcase our research interests, ongoing projects, challenges and future plans. An exciting moment to share our vision and push the boundaries of NLP even further! Hereโs a glimpse of the event! ๐ธโจ
#NLProc
#AI
#Research
#FBK
#Innovation
about 1 year ago
0
2
1
A big congratulations to Sofia Lugli, student of our Carlo Strapparava, for receiving a special mention for her thesis at CLiC-it conference 2 weeks ago! ๐๐ We are incredibly proud of her achievement. Canโt wait to see what she accomplishes next. Well done Sofia!๐
#NLP
#AI
@ailc-nlp.bsky.social
about 1 year ago
0
1
1
๐
#CALAMITA
has officially kicked off - and weโre on board! Fondazione Bruno Kessler proudly participated in this 1st
#evaluation
#campaign
for
#LLMs
with our Andrea Zaninello together with
@fbk-mt.bsky.social
group!๐ค Here some pictures of our calamitici!๐งฒ See u next year 4 other challenges! ๐ฅ๐
about 1 year ago
0
6
3
Exciting news! ๐ If youโre curious about the opening
#tutorial
at CLiC-it 2024 conference made by our group on processing
#data
for
#training
and
#evaluating
#LLMs
, hereโs your chance! ๐ Explore the slides and get inspired!!! ๐๐โจ
docs.google.com/presentation...
@ailc-nlp.bsky.social
loading . . .
Data-LLM-Tutorial
You Are what You Eat Processing Data for Training and Evaluating LLMs Giovanni Bonetta and Bernardo Magnini Fondazione Bruno Kessler, Trento, Italy {gbonetta|magnini}@fbk.eu Tutorial at CLiC-it 2024, ...
https://docs.google.com/presentation/d/1UbzNLWVT3V25OaJ3DZDawtwN4qDg_EKqPuGW50NRJEU/edit#slide=id.g30265607017_0_0
about 1 year ago
0
3
3
Here are our group leader Bernardo Magnini and postdoc Giovanni Bonetta kicking off CLiC-it conference in
#Pisa
2 weeks ago as invited speakers with an insightful
#tutorial
on
#data
: how to collect and use it for various purposes in
#AI
and
#NLP
!๐ก๐ Thanks to
@ailc-nlp.bsky.social
for inviting us!โจ
about 1 year ago
0
4
0
#NLP
Research group in action! Our group leader Bernardo Magnini, alongside
@tizaino.bsky.social
, Sofia Brenna, and Giovanni Bonetta, presenting their
#paper
"Are you a Good Assistant? Assessing LLM Trustability in Task-oriented Dialogues" at CLiC-it '24
#Pisa
๐โจ
@ailc-nlp.bsky.social
#NLProc
#AI
about 1 year ago
0
7
3
What a conference! ๐ CLiC-it in
#Pisa
was truly special! Returning to where it all began a decade ago! โค๏ธ Our group was honored to participate, share ideas and connect with such an inspiring community. Here are some highlights from the conference!!!๐ธโจ
#CLiCit2024
#NLP
#AI
@ailc-nlp.bsky.social
about 1 year ago
0
6
2
๐โจ Happy Holidays from our Research Center! โจ๐ Our director @ferruccioresta shares a warm holiday message with all @FBK_research: gratitude for a year of outstanding achievements and best wishes for a joyful festive season and a 2025 filled with groundbreaking discoveries!
about 1 year ago
0
6
0
you reached the end!!
feeds!
log in