Nando Fioretto
@nandofioretto.bsky.social
Assistant Professor of Computer Science at the University of Virginia. I work on Responsible AI (differential privacy & fairness) and machine learning for science and engineering (differentiable optimization) | http://nandofioretto.github.io
Excited to share that our work "Neuro-Symbolic Generative Diffusion Models" received a DARPA Disruptive Idea Award at NeuS 2025! 🌟
This work pushes toward integrating symbolic reasoning and generative modeling to meet the safety and robustness demands of scientific applications.
This work pushes toward integrating symbolic reasoning and generative modeling to meet the safety and robustness demands of scientific applications.
May 31, 2025 at 1:43 AM
Excited to share that our work "Neuro-Symbolic Generative Diffusion Models" received a DARPA Disruptive Idea Award at NeuS 2025! 🌟
This work pushes toward integrating symbolic reasoning and generative modeling to meet the safety and robustness demands of scientific applications.
This work pushes toward integrating symbolic reasoning and generative modeling to meet the safety and robustness demands of scientific applications.
If you are at #NAACL2025 check out our oral: 🔥
"Speculative Diffusion Decoding: Accelerating Language generation through diffusion"
We use discrete diffusion as a drafting model to speed up #LLM inference---up to 7.2x faster over standard generation 🚀
tiny.cc/xt0i001
"Speculative Diffusion Decoding: Accelerating Language generation through diffusion"
We use discrete diffusion as a drafting model to speed up #LLM inference---up to 7.2x faster over standard generation 🚀
tiny.cc/xt0i001
April 29, 2025 at 11:43 AM
If you are at #NAACL2025 check out our oral: 🔥
"Speculative Diffusion Decoding: Accelerating Language generation through diffusion"
We use discrete diffusion as a drafting model to speed up #LLM inference---up to 7.2x faster over standard generation 🚀
tiny.cc/xt0i001
"Speculative Diffusion Decoding: Accelerating Language generation through diffusion"
We use discrete diffusion as a drafting model to speed up #LLM inference---up to 7.2x faster over standard generation 🚀
tiny.cc/xt0i001
The Privacy Preserving AI workshop is back! And is happening on Monday.
I am excited about our program and lineup of invited speakers!
Check out the program here: ppai-workshop.github.io
I am excited about our program and lineup of invited speakers!
Check out the program here: ppai-workshop.github.io
March 2, 2025 at 12:05 AM
The Privacy Preserving AI workshop is back! And is happening on Monday.
I am excited about our program and lineup of invited speakers!
Check out the program here: ppai-workshop.github.io
I am excited about our program and lineup of invited speakers!
Check out the program here: ppai-workshop.github.io
If you are at #AAAI2025 come and see our oral presentation today in Room 122A at 11:15AM.
The paper "Fairness Issues and Mitigations in (Differentially Private) Socio-demographic Data Processes" shows how sampling errors in survey data can introduce (1/2)
The paper "Fairness Issues and Mitigations in (Differentially Private) Socio-demographic Data Processes" shows how sampling errors in survey data can introduce (1/2)
February 27, 2025 at 12:17 PM
If you are at #AAAI2025 come and see our oral presentation today in Room 122A at 11:15AM.
The paper "Fairness Issues and Mitigations in (Differentially Private) Socio-demographic Data Processes" shows how sampling errors in survey data can introduce (1/2)
The paper "Fairness Issues and Mitigations in (Differentially Private) Socio-demographic Data Processes" shows how sampling errors in survey data can introduce (1/2)
Is there a Machine Learning floor in my hotel?
December 14, 2024 at 1:48 PM
Is there a Machine Learning floor in my hotel?
Huge congratulations to James Kotary on defending his dissertation with flying colors!! 👏🔥🎉
Title of his dissertation: "Integrating Constrained Optimization with Machine Learning to Enhance Data-Driven Decision Making"
j-kota.github.io
Title of his dissertation: "Integrating Constrained Optimization with Machine Learning to Enhance Data-Driven Decision Making"
j-kota.github.io
December 3, 2024 at 1:30 AM
Huge congratulations to James Kotary on defending his dissertation with flying colors!! 👏🔥🎉
Title of his dissertation: "Integrating Constrained Optimization with Machine Learning to Enhance Data-Driven Decision Making"
j-kota.github.io
Title of his dissertation: "Integrating Constrained Optimization with Machine Learning to Enhance Data-Driven Decision Making"
j-kota.github.io
This allows us to generate materials with precise porosity under low training data regimes, human motion synthesis adhering to physical principles, optimize collision-free paths in planning scenarios, and produce video frames simulating motion adhering to ODEs.
w/ Jacob Christopher & Stephen Beak
w/ Jacob Christopher & Stephen Beak
November 18, 2024 at 1:18 AM
This allows us to generate materials with precise porosity under low training data regimes, human motion synthesis adhering to physical principles, optimize collision-free paths in planning scenarios, and produce video frames simulating motion adhering to ODEs.
w/ Jacob Christopher & Stephen Beak
w/ Jacob Christopher & Stephen Beak
Excited to share our #NeurIPS2024 work on combining diffusion models with constrained optimization to generate data adhering to constraints and physical principles (with guarantees!) will be a spotlight at the workshop on AI for Accelerated Materials Design!
🔗 arxiv.org/abs/2402.03559
🔗 arxiv.org/abs/2402.03559
November 18, 2024 at 1:18 AM
Excited to share our #NeurIPS2024 work on combining diffusion models with constrained optimization to generate data adhering to constraints and physical principles (with guarantees!) will be a spotlight at the workshop on AI for Accelerated Materials Design!
🔗 arxiv.org/abs/2402.03559
🔗 arxiv.org/abs/2402.03559