Benedetta Liberatori

PhD student @UniTrento

[Benedetta Liberatori @bliberatori_]

What does it really mean for two videos to be similar?

At #NeurIPS2025, we’ll present ConViS-Bench: Estimating Video Similarity Through Semantic Concepts.

Stop by our poster for a chat!
📍Exhibit Hall C,D,E — Poster N.4618
🕒 Thu, Dec 4, 2025 • 11:00 AM – 2:00 PM PST

[Multimedia & Human Understanding Group (MHUG) @mhug_unitn]

🙏 CVPR is a wrap for the MHUG lab! A huge thank you to everyone who stopped by our posters, asked questions, and shared ideas. It’s been an incredible few days. See you next year! 👋 #CVPR2026

More pics from our posters 👇

[Paolo Rota @CVPR @paolorotaphd]

Hedwig started her keynote... Hurry up in room 111.

#cvpr2026

[Paolo Rota @CVPR @paolorotaphd]

Ranjay is giving his keynote speech right now! Room 111!!!

#cvpr2026

[Paolo Rota @CVPR @paolorotaphd]

Andrei Bursuc is now on!

#Cvpr2026 - room 111

[Paolo Rota @CVPR @paolorotaphd]

Georgia Gkioxari in room 111 now presenting at MULA workshop

[Nicolas Sereyjol-Garros @sg_nicolas]

Come see our poster tomorrow afternoon at #ICRA2026 to talk about 3D representation alignment of diffusion models for LiDAR generation.

📍196, Hall C
🗓️ Wednesday, 3:00-4:30 PM

[valeo.ai @valeoai]

Our recent research will be presented at #CVPR2026 @CVPR!
We’ll present nine papers in the main conference & one in the Findings track.
We’ll be speaking in two workshops & one tutorial
Here is a quick overview on the works we’ll be presenting in Denver:
https://t.co/nFZ8wvkuRr

[Benedetta Liberatori @bliberatori_]

@valeoai Thanks for having me!

[Sophia Sirko-Galouchenko @sophia_sirko]

1/n New paper - V-GIFT 🎁

Self-supervised tasks like rotation prediction or colorization were big in 2018.
Do they still matter?

Yes.
We turn them into visual instruction tuning data for MLLMs.

Result: models rely more on the image and perform better on vision tasks 👀

[Multimedia & Human Understanding Group (MHUG) @mhug_unitn]

Huge congrats to our colleague and friend @lucazanella95 on his graduation! 🎓
Brilliant researcher, great teammate, and a wonderful person, we’re proud to celebrate this milestone with you, Luca! Looking forward to what comes next 💪

[Marco Garosi @CVPR26 @marco_garosi]

🚨 Are we underestimating Large Multimodal Models for classification?

We challenged the status quo in our new paper from @mhug_unitn, "Large Multimodal Models as General In-Context Classifiers", accepted at #CVPR2026 Findings 🔥

A quick thread on our discoveries 🧵👇1/7

[Multimedia & Human Understanding Group (MHUG) @mhug_unitn]

We are so back 😎

[Thomas De Min @tdemin99]

Can MLLMs ask for help? 🤔
When facing an unanswerable visual query, models typically hallucinate or abstain. We argue there's a better option: being proactive and requesting a simple user intervention.
Introducing ProactiveBench! 🧵

[Shiyao Xu @xusy2333]

Just in case you miss us! DEMO is now in #3DV2026 poster session 3, N.20!

We propose a new task: Dense Motion Captioning, together with the dataset: CompMo (60k, ~40s duration) and the model: DEMO for the task

🕺🏽project page: https://t.co/ikL1gShbiY
come and say hi (virtually!)

[Shiyao Xu @xusy2333]

working on human motion and in #3DV206 ?
then don’t miss this interesting work!
in “Dense Motion Captioning”, the authors propose a new task, dataset, and the model for dense 3D human motion captioning

[Paolo Rota @CVPR @paolorotaphd]

The deadline is coming… and it waits for no one. 🐺

📚 MULA workshop submissions close tomorrow (March 9)

Details: https://t.co/n66pA6N9qg
#CVPR2026

[Paolo Rota @CVPR @paolorotaphd]

🎉 Big news! 🎉
We’re excited to announce that the 9th edition of the Multimodal Learning and Application Workshop (MULA) will be held at CVPR 2026 in Denver as a full-day workshop!

#CVPR2026

[Thomas De Min @tdemin99]

I'm happy to announce that our latest paper, “Group-Robust Machine Unlearning,” has been accepted at TMLR!
📄 https://t.co/Qidr8P1Wyt

[Benedetta Liberatori @bliberatori_]

Check out the project page to see more: https://t.co/ReutJiyBq9

Huge thanks to my coauthors: @altndrr , Lorenzo Vaquero Otal, @YimingWang107 , @eliricci_ , @paolorotaphd.

[Benedetta Liberatori @bliberatori_]

What does it really mean for two videos to be similar?

At #NeurIPS2025, we’ll present ConViS-Bench: Estimating Video Similarity Through Semantic Concepts.

Stop by our poster for a chat!
📍Exhibit Hall C,D,E — Poster N.4618
🕒 Thu, Dec 4, 2025 • 11:00 AM – 2:00 PM PST