Maximo Rulli (@MaximoRulli) profile picture

Studying how machines learn 🤖 and teaching them some things 🧠⚙️ CS @SapienzaRoma

Joined October 2025
Photo by Maximo Rulli (@MaximoRulli)Photo by Maximo Rulli (@MaximoRulli)Photo by Maximo Rulli (@MaximoRulli)Photo by Maximo Rulli (@MaximoRulli)Photo by Maximo Rulli (@MaximoRulli)Photo by Maximo Rulli (@MaximoRulli)Photo by Maximo Rulli (@MaximoRulli)
You shouldn’t need a PhD to start doing serious AI research. We’re launching BAINSA Sapienza, a student-led AI research lab where ambitious students move from reading papers to doing research. Applications are open: forms.gle/omhoy5LPxTfuh6Mm8 For those who aspire to build.
1
1
4
72
Introducing NVIDIA Object Oriented Agents (NOOA), probably the most Pythonic way to build AI agents 🐍 In NOOA, an agent is just a Python class. If you know Python, you already know NOOA. And yes, building agents can be this simple ↓
7
15
45
3,267
Maximo Rulli retweeted
1/ Large Language Models leak energy when they hallucinate. We built a training-free method to catch the spill and keep them *grounded*. Our #ICLR2026 paper introduces Spilled Energy for SOTA zero-shot detection. TLDR: Hallucinations violate the probability chain rule.
7
31
2
192
11,992
*Attention Sinks in Diffusion Language Models* by @MaximoRulli @devoto_alessio @simone_petruzzi @fabreetseo We study attention sinks in diffusion models, with many findings including "moving" sinks and a strong robustness of the underlying models. arxiv.org/abs/2510.15731
25
171
9,642
Attention sinks emerge in Diffusion LLMs too, but they move around! 👀 We find that: sinks shift positions during generation & Diffusion models are surprisingly robust to masking them! ⚡️ w/ @MaximoRulli @simone_petruzzi @s_scardapane @fabreetseo
9
34
2
155
10,694