Karush Suri

I am a research engineer at Valence Labs with Dominique Beaini and Emmanuel Bengio. Previously I was an AI Resident at Google X with Lam Nguyen. I completed my M.A.Sc in ECE at UToronto with Kostas Plataniotis and Yuri Lawryshyn.

[github]   [google scholar]   [linkedin]   [bsky]   [x]   [email]

Publications

α = Equal Contribution

Understanding Conditional Computation in Contrastive Phenomic Retrieval
K Suri, P Moghadam, F Wenkel, M Sypetkowski, E Bengio, E Noutahi, D Beaini
Technical Report 2025
[paper]

How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval
P Fradkinα, P Azadiα, K Suri, F Wenkel, A Bashashati, M Sypetkowski, D Beaini
NeurIPS 2024
FM4S @ NeurIPS 2024 (oral) (Best Paper Award)
[paper]  [reviews]

On the Scalability of GNNs for Molecular Graphs
M Sypetkowski, F Wenkel, F Poursafei, N Dickson, K Suri, P Fradkin, D Beaini
NeurIPS 2024
[paper]  [code]  [blog]  [reviews]

Surprise Minimizing Multi-Agent Learning with Energy-based Models
K Suri, X Q Shi, K Plataniotis, Y Lawryshyn
NeurIPS 2022
[paper]  [webpage]  [code]  [talk]  [reviews]

Off-Policy Evolutionary Reinforcement Learning with Maximum Mutations
K Suri
AAMAS 2022. (oral)
[paper]  [webpage]  [code]  [talk]  [reviews]

Continuous Sign Language Recognition from Wearable IMUs using CapsNet and Game Theory
K Suri, R Gupta
CEE, Elsevier, Vol. 78, 2019.
[paper]  [code]  [demo]  [reviews]

Transfer Learning for sEMG-based Hand Gesture Classification using Master-Slave Nets
K Suri, R Gupta
IEEE IC3I 2018.
[paper]

Theses

Deep Hierarchical Reinforcement Learning
MASc thesis, 2021
University of Toronto
[link]

Application of Deep Learning and Game Theory for Sign Language Recognition using Wearable Sensors
BTech thesis, 2019
Amity University
[link]