Hao Song

Applied Scientist, Amazon

Joined

July 2019

Names

Hao Song

Emails

****@gmail.com (Confirmed)

****@bristol.ac.uk (Confirmed)

****@outlook.com (Confirmed)

****@amazon.com (Confirmed)

Personal Links

Google Scholar

Career & Education History

Applied Scientist

Amazon (amazon.com)

2023 – Present

ML researcher

Seldon (seldon.io)

2021 – 2023

Lecturer

University of Bristol (bristol.ac.uk)

2020 – 2021

Postdoc

University of Bristol (bristol.ac.uk)

2017 – 2021

PhD student

University of Bristol (bristol.ac.uk)

2014 – 2017

Advisors, Relations & Conflicts

No relations added

Expertise

Probabilitic Calibration

Present

Uncertainty Quantification

Present

Publications

Token-Wise Residual Latent Adapters: Steering Seq2Seq Models for Protein Fitness Extrapolation
Steven Wu, Mostafa Karimi, Sharmi Banerjee, Peng Gao, Jonah Noh, Jiachen Li, Robert Jiang, Bella Dubrov, Shang Shang, Hao Song
- GenBio 2026 Poster
- Readers: Everyone
Classifier Calibration: How to assess and improve predicted class probabilities: a survey
Telmo de Menezes e Silva Filho, Hao Song, Miquel Perelló-Nieto, Raúl Santos-Rodríguez, Meelis Kull, Peter A. Flach
- 2021 (modified: 24 Apr 2023)
- CoRR 2021
- Readers: Everyone
Efficient and Robust Model Benchmarks with Item Response Theory and Adaptive Testing
Hao Song, Peter A. Flach
- 2021 (modified: 24 Apr 2023)
- Int. J. Interact. Multim. Artif. Intell. 2021
- Readers: Everyone
Modelling Patient Behaviour Using IoT Sensor Data: a Case Study to Evaluate Techniques for Modelling Domestic Behaviour in Recovery from Total Hip Replacement Surgery
Michael Holmes, Miquel Perelló-Nieto, Hao Song, Emma Tonkin, Sabrina Grant, Peter A. Flach
- 2020 (modified: 24 Apr 2023)
- J. Heal. Informatics Res. 2020
- Readers: Everyone
Distribution calibration for regression
Hao Song, Tom Diethe, Meelis Kull, Peter A. Flach
- 2019 (modified: 11 Nov 2022)
- ICML 2019
- Readers: Everyone
Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with Dirichlet calibration
Meelis Kull, Miquel Perelló-Nieto, Markus Kängsepp, Telmo de Menezes e Silva Filho, Hao Song, Peter A. Flach
- 2019 (modified: 24 Apr 2023)
- NeurIPS 2019
- Readers: Everyone
Releasing eHealth Analytics into the Wild: Lessons Learnt from the SPHERE Project
Tom Diethe, Mike Holmes, Meelis Kull, Miquel Perelló-Nieto, Kacper Sokol, Hao Song, Emma Tonkin, Niall Twomey, Peter A. Flach
- 2018 (modified: 16 Jul 2019)
- KDD 2018
- Readers: Everyone
Analysis of Patient Domestic Activity in Recovery From Hip or Knee RePlacement Surgery: Modelling Wrist-worn Wearable RSSI and Accelerometer Data in The Wild
Mike Holmes, Hao Song, Emma Tonkin, Miquel Perelló-Nieto, Sabrina Grant, Peter A. Flach
- 2018 (modified: 16 Jul 2019)
- KHD@IJCAI 2018
- Readers: Everyone
The SPHERE Challenge: Activity Recognition with Multimodal Sensor Data
Niall Twomey, Tom Diethe, Meelis Kull, Hao Song, Massimo Camplani, Sion L. Hannuna, Xenofon Fafoutis, Ni Zhu, Pete Woznowski, Peter A. Flach, Ian Craddock
- 2016 (modified: 02 Sept 2025)
- CoRR 2016
- Readers: Everyone
Subgroup Discovery with Proper Scoring Rules
Hao Song, Meelis Kull, Peter A. Flach, Georgios Kalogridis
- 2016 (modified: 24 Apr 2023)
- ECML/PKDD (2) 2016
- Readers: Everyone

Co-Authors

View all 29 co-authors