Researcher at Qualcomm AI Research Netherlands
Amsterdam, The Netherlands
Joined February 2022
- Tweets17
- Following58
- Followers34
- Likes10
Fabio Valerio Massoli retweeted
🚨With my PhD coming to an end, it's time for a life update! I've recently joined @Qualcomm AI Research as a Senior Machine Learning Researcher. Looking forward to working with this great team!🧠✨
Fabio Valerio Massoli retweeted
Join @noor_fathima_ and myself this afternoon at #CVPR2024 to learn more about Clockwork Diffusion :) Highlight poster #345, from 5pm in Arch 4A-E
Interested in fast diffusion models? We will be presenting Clockwork at #CVPR2024.
Paper: arxiv.org/abs/2312.08128
Code: github.com/qualcomm-ai-resea…
Fabio Valerio Massoli retweeted
Thrilled that a paper from my PhD, "Faster Maximum Inner Product Search in High Dimensions" has been accepted to ICML 2024!
In the paper, we accelerate state-of-the-art for the Maximum Inner Product Search (MIPS) problem. MIPS is a core subroutine in systems like recommendation engines, multi-class prediction, matching pursuit, retrieval, and more. We improve the state-of-the-art by using techniques from multi-armed bandits.
Paper: arxiv.org/abs/2212.07551
Let me know if you'll be in Vienna for ICML!
Congratulations to my coauthors Ryan Kang, Donghyun (Luke) Lee, Jeyong Lee, @chrispiech, @SebastianThrun, @ilanshom, and @martinjzhang!
Fabio Valerio Massoli retweeted
Here's one for the physicists: we built a transformer that's equivariant to the Lorentz symmetry of special relativity.
Super fun project led by @jonas_spinner and @victorbreso, plus @pimdehaan, Tilman Plehn, @jessethaler.
arxiv.org/abs/2405.14806
Excited to share the Lorentz-equivariant Geometric Algebra Transformer (L-GATr) for high-energy physics.
w/ @victorbreso @pimdehaan @jessethaler Tilman Plehn and @johannbrehmer
arxiv.org/abs/2405.14806
Fabio Valerio Massoli retweeted
Are you dealing with geometric data, be it from molecules or robots? Would you like inductive biases *and* scalability?
Our Geometric Algebra Transformer (GATr 🐊) may be for you.
New work w/ @pimdehaan, Sönke Behrends, and @TacoCohen:
arxiv.org/abs/2305.18415
1/9
Fabio Valerio Massoli retweeted
Our NeurIPS workshop "A causal view on dynamical systems" is coming closer! 🔥🔥
We are excited to receive contributions until Sept. 22 AoE (⚠️10 days left!!)
🔄 Check out our website: sites.google.com/view/caudyn…
Hope to see you in New Orleans or virtually on Dec. 3rd!
Fabio Valerio Massoli retweeted
“Heating or Eating” is the new slogan for the coming winter. The war in Ukraine will be felt in many homes across Europe. And every month the divide between Europe and Russia grows bigger. Sad. dw.com/en/world-in-progress-…
Fabio Valerio Massoli retweeted
Join us in 15 min!
This Tuesday Jinwoo Kim presents his recent "Pure Transformers are Powerful Graph Learners"! arxiv.org/abs/2207.02505
Just tokenize the edges as well and throw everything in a "pure" transformer.
Join the discussion on Zoom at 11am EST / 3pm UTC tomorrow: hannes-stark.com/logag-readi…
Finally, our survey
A Leap among Quantum Computing and Quantum Neural Networks: A Survey
dl.acm.org/doi/10.1145/35297…
has been published!!!
Enjoy a (quantum) leap among models and theories 🤣🍻🥂
#QuantumComputing #QuantumNeuralNetworks #QuantumMachineLearning #QNN #QML
Fabio Valerio Massoli retweeted
Our new paper is out!🧬
EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction arxiv.org/abs/2202.05146
Fast 3D structure predictions in which molecules bind to proteins!
With the lovely team @octavianEganea @lucky_pattanaik @BarzilayRegina Tommi Jaakkola 🤗
1/2
Fabio Valerio Massoli retweeted
"A Leap among Quantum Computing and Quantum Neural Networks: A Survey" is now available on arxiv
lnkd.in/eyjWatTT
In the survey we analyze state-of-the-art QNN models, discuss about training issues on NISQ devices, report about qubit technologies, ... and much more :)
Don't forget to check the repo
github.com/fvmassoli/survey-…
Lots of QNNs papers already collected
"A Leap among Quantum Computing and Quantum Neural Networks: A Survey" is now available on arxiv
lnkd.in/eyjWatTT
In the survey we analyze state-of-the-art QNN models, discuss about training issues on NISQ devices, report about qubit technologies, ... and much more :)