Babak Ehteshami Bejnordi

I am a research scientist at Qualcomm AI Research (Senior Staff Engineer and Manager). My primary research focus lies in the realm of efficient Deep Learning for Large Language Models (LLMs) and Computer Vision. My recent research works have been in the areas of Efficient Autoregressive decoding in LLMs, Mixture of Experts, Multi-Task Learning, and Continual Learning. I am leading a team on Conditional Computation for efficient deep learning.

I have been the organizer of the Qualcomm Innovation Fellowship Program in Europe since 2019.

I obtained my PhD under the supervision of Prof. Nico Karssemeijer and Prof. Jeroen van der laak at the Diagnostic Image Analysis Group, Radboud University, the Netherlands, where I worked on the development of machine learning algorithms for detection and characterization of breast cancer in histopathology images. During my PhD, I also organized the CAMELYON16 challenge on breast cancer metastases detection.

From Jun to Nov 2016, I was a visiting researcher at Harvard University.

Latest news

09 Dec 2024: We will be demoing our Cache-MoE running efficiently on a smartphone at NeurIPS'24
05 Dec 2024: We bring Mixture of Experts (MoE) to mobile devices with limited available DRAM
26 Sep 2024: Check out our NeurIPS'24 and BMVC'24 papers on Efficient MoE and Multi-task learning
21 Sep 2023: Check out our NeurIPS'23 paper: Scalarization for Multi-Task and Multi-Domain Learning at Scale
25 Jul 2023: We organized the Resource Efficient DL for CV workshop at ICCV'23
06 Apr 2023: I will be teaching at DeepLearn 2023 - 9th International School on Deep Learning in Bari, Italy
03 Jul 2022: Efficient video object detection paper accepted at ECCV22
13 Jul 2021: Keynote talk at the ELLIS PhD and Postdoc Summit (kick-off program).
10 Jul 2021: We open-sourced the code for FrameExit and SkipConvolutions.
06 Mar 2021: Two papers accepted at CVPR2021 FrameExit (Oral paper) and Skip-Convolutions.
22 Jun 2020: Check out my podcast interview with TWIML AI on Conditional Computation.
24 FEB 2020: Check out our CVPR 2020 Oral paper on channel gated networks for continual learning.
20 Dec 2019: My paper "Batch-shaping for learning conditional channel gated nets" is accepted at ICLR 2020.
02 Dec 2018: My work on real-time human pose estimation on mobile devices was demoed at NeurIPS.
22 Jun 2018: My interview with the Cancer Today Magazine is published.
16 Jun 2018: My latest work in collaboration with Harvard, NIH, and Mayo Clinic is published.
20 Dec 2017: I defended my PhD in public: video recording
12 Dec 2017: Follow the Altmetric Attention Score and Tweets for my Article in JAMA
12 Dec 2017: My paper is published in JAMA
07 Dec 2016: CAMELYON16 won the 2016 MedicalPhit Innovation Award
16 Nov 2016: I gave a talk on deep learning at the Broad Institute of MIT and Harvard
10 Oct 2016: CAMELYON16 was mentioned in the White House AI strategic planning report
15 Oct 2015: I started organizing the CAMELYON16 challenge