Bilal Alsallakh

Principal Researcher, Voxel AI

Joined

September 2020

Names

Bilal Alsallakh (Preferred)

Emails

****@fb.com (Confirmed)

****@meta.com (Confirmed)

****@gmail.com (Confirmed)

****@voxelai.com (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

Principal Researcher

Voxel AI (voxelai.com)

2022 – Present

Researh Scientist

Meta AI (facebook.com)

2019 – 2022

Researh Scientist

Bosch Research North America (bosch.com)

2015 – 2019

Postdoc

Harvard University (harvard.edu)

2014 – 2015

PhD student

TU Wien Vienna University of Technology (tuwien.ac.at)

2010 – 2014

Advisors, Relations & Conflicts

No relations added

Expertise

Explainable AI

2017 – Present

Visualizing Deep Neural Networks

2016 – Present

Computer Vision

2006 – Present

Publications

On Symmetries in Convolutional Weights
Bilal Alsallakh, Timothy J Wroge, Vivek Miglani, Narine Kokhlikyan
- ICLR 2025 Workshop Weight Space Learning Poster
- Readers: Everyone
Detrimental Memories in Transfer Learning
Amal Alnouri, Timothy J Wroge, Bilal Alsallakh
- TF2M 2024 Poster
- Readers: Everyone
What Happens to the Source Domain in Transfer Learning?
Amal Alnouri, Bilal Alsallakh
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
Mind the Pool: Convolutional Neural Networks Can Overfit Input Size
Bilal Alsallakh, David Yan, Narine Kokhlikyan, Vivek Miglani, Orion Reblitz-Richardson, Pamela Bhattacharya
- Published: 01 Feb 2023, Last Modified: 27 Feb 2023
- ICLR 2023 poster
- Readers: Everyone
Bias Mitigation Framework for Intersectional Subgroups in Neural Networks
Narine Kokhlikyan, Bilal Alsallakh, Fulton Wang, Vivek Miglani, Aobo Yang, David Adkins
- 22 Sept 2022 (modified: 13 Feb 2023)
- ICLR 2023 Conference Withdrawn Submission
- Readers: Everyone
Are Convolutional Networks Inherently Foveated?
Bilal Alsallakh, Vivek Miglani, Narine Kokhlikyan, David Adkins, Orion Reblitz-Richardson
- Published: 02 Nov 2021, Last Modified: 05 May 2023
- SVRHM 2021 Poster
- Readers: Everyone
Debugging the Internals of Convolutional Networks
Bilal Alsallakh, Narine Kokhlikyan, Vivek Miglani, Shubham Muttepawar, Edward Wang, Sara Zhang, David Adkins, Orion Reblitz-Richardson
- Published: 17 Oct 2021, Last Modified: 05 May 2023
- XAI 4 Debugging Workshop @ NEURIPS 2021 Poster
- Readers: Everyone
Convolution Can Incur Foveation Effects
Jun Yuan, Bilal Alsallakh, Narine Kokhlikyan, Vivek Miglani, Orion Reblitz-Richardson
- Published: 14 Apr 2021, Last Modified: 24 May 2023
- Rethinking ML Papers - ICLR 2021 workshop Poster
- Readers: Everyone
Mind the Pad -- CNNs Can Develop Blind Spots
Bilal Alsallakh, Narine Kokhlikyan, Vivek Miglani, Jun Yuan, Orion Reblitz-Richardson
- Published: 12 Jan 2021, Last Modified: 12 Oct 2025
- ICLR 2021 Spotlight
- Readers: Everyone
Investigating Saturation Effects in Integrated Gradients
Vivek Miglani, Narine Kokhlikyan, Bilal Alsallakh, Miguel Martin, Orion Reblitz-Richardson
- 2020 (modified: 05 Nov 2022)
- CoRR 2020
- Readers: Everyone

View all 13 publications