Alessandro Conti

Machine Learning Researcher @Tavus, prev @Apple, Ph.D. @UniTrento

[Tavus @tavus]

Introducing Phoenix-4, the most advanced real-time human rendering model ever built.

Its the first real-time model to render every pixel at runtime, generate and control emotional states, listen actively, and actually behave the way humans do in conversation.

[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

[Francesco Tonini @toninifrancesco]

Dublin, here we come! 🇮🇪 Our paper "Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection" has been accepted to #ACMMM2025

[Alessandro Conti @altndrr]

Thanks to the greatest @massi_manc, @DonkeyShot21,
@YimingWang107, @paolorotaphd, and
@eliricci_ for their support — couldn’t have done it without you! 🙏🏻

📄 Abstract: https://t.co/7M1SgyXc7w
💻 Code: https://t.co/lEiNCw7J2e

[Alessandro Conti @altndrr]

What if we stopped treating image classification like a multiple-choice quiz…
…and just asked the model: "What’s in this image?"

Our paper on open-world classification with LMMs got into #ICCV2025! 🎉🌺

Let’s talk failures, insights, and flipping mistakes 👇

[Alessandro Conti @altndrr]

We try prompting + reasoning strategies to flip wrong → right and generic → specific.

They help, but it’s clear that open-world classification is still very challenging for today’s LMMs.

[Alessandro Conti @altndrr]

I also got a minimalistic reviewer. Guess the rating

[Arturs Berzins @artuursberzins]

The state of peer-review in ML:

[Alessandro Conti @altndrr]

@paolorotaphd @cooltechtipz This is different one but will add it to the list of tricks for vision conferences

[Yiming Wang @YimingWang107]

Our T3AL 🦆 poster has been picked by @CVPR daily! Come by and talk to @bliberatori_ @altndrr @paolorotaphd me, and @eliricci_ in the afternoon session!

[Alessandro Conti @altndrr]

This is incredible🤯

At test-time, ONE unlabelled video is enough to teach CLIP-like models to localize actions in time despite their lack of prior knowledge of the time domain.

More on our @CVPR paper below 👇

[Benedetta Liberatori @bliberatori_]

🤔 Can we localize & classify actions in untrimmed videos without training data?

We introduce T3AL🦆, a method that performs zero-shot temporal action localization by learning only at test-time on unlabeled video data.

Accepted @ #CVPR2024 !
Webpage: https://t.co/qlkkqjC5CQ

[Yiming Wang @YimingWang107]

Glad to announce that the 1st Workshop on Green Foundation Models (GreenFOMO) is happening @eccvconf Milan, 2024🥳
Can't wait to see what impact our community can make towards a green world 🌏and an inclusive AI💚!
Official website + CfP coming soon...Stay tuned😉

[Alessandro Conti @altndrr]

@chrisalbon this is a good one, also quite recent

https://t.co/tnNLwhfdbK

[Alessandro Conti @altndrr]

@udoooom @CVPR @naoto_inoue_ @ktrk115 @kotymg おめでとう!

[Paul Fairie @paulisci]

A List of Predictions Made in 1924 About 2024

🧵

[Antonio Norelli @noranta4]

Cool universal classifier that leverage a knowledge database. You take a pic and get a class, without having defined the classes in advance.

[Alessandro Conti @altndrr]

@giffmana Currently at NeurIPS and missing that feeling and coding in general 👀

[Alessandro Conti @altndrr]

Card design by @taapstudio, check out their Instagram profile (https://t.co/D7x8xDpQI6)! 🔥

[Alessandro Conti @altndrr]

Do you know the names of these animals? 🦆🐑🐖

Tomorrow morning at #NeurIPS (poster #201), we will gift these cards and more to try the demo of our method CaSED! 🔥

Try it now (https://t.co/GgDqhgijaq) and classify images with CLIP without a predefined list of class names! 🚀