Indro Spinelli
@IndroSpinelli
Followers
360
Following
1K
Media
26
Statuses
228
Assistant Professor @SapienzaRoma | @ELLISforEurope member. Fascinated by #VirtualHumans, exploring everything from human-robot🤖interaction to #Neuroscience 🧠
Rome
Joined December 2011
freshly unboxed under the Roman sun! ☀️ A massive thank you to @NVIDIAAIDev and the #NVIDIAGrant program for this opportunity. Time to teach some robots how to speak! 🚀
0
0
7
Absolute banger from these department colleagues!
LLMs are injective and invertible. In our new paper, we show that different prompts always map to different embeddings, and this property can be used to recover input tokens from individual embeddings in latent space. (1/6)
0
0
1
Join us at poster 88 to discuss MonSTeR: a unified model for motion, scene and text retrieval!
0
1
5
You will find the entire team with @LucaCollorone @orlitany @GalassoFab10 and more from the @SapienzaPINlab
0
0
4
Just landed in Honolulu for ICCV 25! You can read MonSTeR here: https://t.co/E4idFd4PxZ and then find us at Poster Session 3 #1003 🗓 Oct 22 | 11:15 a.m. - 1:15 p.m. HST - Exhibit Hall I
arxiv.org
Intention drives human movement in complex environments, but such movement can only happen if the surrounding context supports it. Despite the intuitive nature of this mechanism, existing research...
TtA (Thrilled to announce) that our paper, "MonSTeR: A Unified Model for Motion, Scene, and Text Retrieval" has been accepted at #ICCV2025 🌋🌺🌴🌊🏄♂️🍹 MonSTeR creates a unified latent space that understands the relationship between text, human motion, and 3D scenes.
1
1
10
Children learn to manipulate the world by playing with toys — can robots do the same? 🧸🤖 We show that robots trained on 250 "toys" made of 4 shape primitives (🔵,🔶,🧱,💍) can generalize grasping to real objects. @JitendraMalikCV @trevordarrell Shankar Sastry @berkeley_ai😊
3
29
140
We are getting ready for the second edition of Beyond Euclidean Workshop @ICCVConference We hope to see you there on Sunday!
0
5
8
Back in Rome after an incredible visiting period at @TU_Muenchen. Thanks @BusamBenjamin & @NassirNavab for hosting. It was amazing to see the latest in medical robotics and its democratisation, meet new people, and present @SapienzaPINlab's work! The slide lived up to the hype🎢
0
0
15
Code and preprint will follow. In the meantime huge thanks to @LucaCollorone for being a Beatles' fan (and a great researcher), @orlitany for this awesome collaborations, to the others @SapienzaPINlab co-authors and its head @GalassoFab10 that contributed to this achievement!
0
0
3
It's not just about matching intent with action🗣️🕺; it's about verifying if the environment🌍 allows for it. We believe this is a significant step towards creating more plausible and grounded human-scene interactions.
1
0
2
As @thebeatles sang, "She asked me to stay and she told me to sit anywhere. But I looked around and I noticed there wasn't a chair." MonSTeR can determine the coherence between a textual command and a motion within a given scene 🧠🪑.
1
0
1
TtA (Thrilled to announce) that our paper, "MonSTeR: A Unified Model for Motion, Scene, and Text Retrieval" has been accepted at #ICCV2025 🌋🌺🌴🌊🏄♂️🍹 MonSTeR creates a unified latent space that understands the relationship between text, human motion, and 3D scenes.
1
2
8
Clock is ticking!
Paper submission deadline for our @ICCVConference workshop has been extended to 27th of June! Plenty of time to work on a paper submission off the back of @CVPRConf @CVPR @TheBMVA @eccvconf @PascalMettes @adn_twitts @IndroSpinelli
0
0
0
Your paper didn’t make it to the main conference @ICCVConference why not consider our workshop instead?
Paper submission deadline for our @ICCVConference workshop has been extended to 27th of June! Plenty of time to work on a paper submission off the back of @CVPRConf @CVPR @TheBMVA @eccvconf @PascalMettes @adn_twitts @IndroSpinelli
0
2
2
🚨 We're hiring a Postdoc in Robot Learning @ PEARL Lab, TU Darmstadt 🚨 Join our ERC-funded project SIREN (Structured Interactive Perception and Learning for Holistic Robotic Embodied Intelligence). We’re developing methods that will enable robots to understand and adapt to
pearl-lab.com
We are seeking for Postdocs to join our group and contribute to the ERC StG SIREN, and the Excellence Clusters RAI and TAM. Job descriptions: Job Post 1, Job Post 2 We are hiring PhD students only …
0
11
35
Paper submission deadline for our @ICCVConference workshop has been extended to 27th of June! Plenty of time to work on a paper submission off the back of @CVPRConf @CVPR @TheBMVA @eccvconf @PascalMettes @adn_twitts @IndroSpinelli
We are back at #ICCV2025 for the second workshop on Hyperbolic and Hyperspherical Learning for Computer Vision. We will have 2 tracks: one for new research (to be published in proceedings) and one for recently published works. Deadline: June 1st Link:
0
6
19
📢The Beyond Euclidean Workshop gets its deadline extended!! So, if you have bad news from @ICCVConference , you could turn them around New deadline: June 27! https://t.co/BPJhG0j9O5 The review will be tight, so, if you want to help reviewing please reach out.
sites.google.com
Important Dates: Submission Portal Opens: 29th of April 2025 Submission Deadline: 27th of June 2025 (AOE) Preliminary Author Notification Deadline: 10th of July 2025 Camera-ready deadline (Proceedi...
0
2
2
Beyond Euclidean (2nd Ed.) @ICCVConference workshop's call for papers is still open! Check out the details here: https://t.co/U5KuvihZtg 📅 Deadline: **15th June**! We have a full proceedings track and a short paper (non-archival) option. Don’t miss out!
0
3
6
After a very successful 1st edition at @eccvconf our Beyond Euclidean workshop is back, now at @ICCVConference in October! We will update our webpage ( https://t.co/iG9GlqLxAH) with information on our keynote speakers and open a call for full and short papers in the coming days!
sites.google.com
Bringing together researchers to uncover the principles of Non-euclidean representations. Within deep learning, Euclidean geometry is the default basis for deep neural networks, yet the naive...
1
17
63