Daniel Severo

Orcid: 0000-0003-0472-5300

Affiliations:
  • Meta, FAIR Labs, Montréal, Canada
  • University of Toronto, Department of Electrical & Computer Engineering, ON, Canada (PhD 2022)
  • Vector Institute for Artificial Intelligence, Toronto, ON, Canada (former)
  • 3778 Healthcare, São Paulo, Brazil (former)


According to our database1, Daniel Severo authored at least 21 papers between 2019 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking.
CoRR, May, 2025

Learning Distributions over Permutations and Rankings with Factorized Representations.
CoRR, May, 2025

Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search.
CoRR, January, 2025

Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Enhancing and Evaluating Probabilistic Circuits for High-Resolution Lossless Image Compression.
Proceedings of the Data Compression Conference, 2025

2024
Random Permutation Codes: Lossless Source Coding of Non-Sequential Data.
CoRR, 2024

Practical Shuffle Coding.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Random Cycle Coding: Lossless Compression of Cluster Assignments via Bits-Back Coding.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Entropy Coding of Unordered Data Structures.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
Random Edge Coding: One-Shot Bits-Back Coding of Large Labeled Graphs.
CoRR, 2023

Action Matching: Learning Stochastic Dynamics from Samples.
Proceedings of the International Conference on Machine Learning, 2023

One-Shot Compression of Large Edge-Exchangeable Graphs using Bits-Back Coding.
Proceedings of the International Conference on Machine Learning, 2023

2022
Compressing Multisets With Large Alphabets.
IEEE J. Sel. Areas Inf. Theory, December, 2022

Action Matching: A Variational Method for Learning Stochastic Dynamics from Samples.
CoRR, 2022

Data-Driven Optimization for Zero-Delay Lossy Source Coding with Side Information.
Proceedings of the IEEE International Conference on Acoustics, 2022

2021
Predição de Incidência de Lesão por Pressão em Pacientes de UTI usando Aprendizado de Máquina.
CoRR, 2021

Regularized Classification-Aware Quantization.
CoRR, 2021

Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding.
Proceedings of the 38th International Conference on Machine Learning, 2021

2020
Predicting Multiple ICD-10 Codes from Brazilian-Portuguese Clinical Notes.
Proceedings of the Intelligent Systems - 9th Brazilian Conference, 2020

2019
Ward2ICU: A Vital Signs Dataset of Inpatients from the General Ward.
CoRR, 2019


  Loading...