activity
20242026
most citedLL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons

5 citations · 5 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Pitfalls of Unlabeled Disagreement-Based Drift Detection in Streaming Tree Ensembles

Lara Sá Neves, Afonso Lourenço, Lizy K. John +1

Detecting concept drift in high-speed data streams remains challenging, particularly when models must operate on unlabeled data and avoid false alarms caused by benign shifts. Whil…

cs.LG2026

From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips

Alan T. L. Bacellar, Sathvik Chemudupati, Shashank Nag +4

The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors. While empirical studies indicat…

cs.LG20255 cited

LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons

Shashank Nag, Alan T. L. Bacellar, Zachary Susskind +9

Vision Transformers have been tremendously successful in computer vision tasks. However, their large computational, memory, and energy demands are a challenge for edge inference on…

cs.LG2025

nanoML for Human Activity Recognition

Alan T. L. Bacellar, Mugdha P. Jadhao, Shashank Nag +3

Human Activity Recognition (HAR) is critical for applications in healthcare, fitness, and IoT, but deploying accurate models on resource-constrained devices remains challenging due…

cs.LG2024

Shrinking the Giant : Quasi-Weightless Transformers for Low Energy Inference

Shashank Nag, Alan T. L. Bacellar, Zachary Susskind +9

Transformers are set to become ubiquitous with applications ranging from chatbots and educational assistants to visual recognition and remote sensing. However, their increasing com…

cs.LG2024

Differentiable Weightless Neural Networks

Alan T. L. Bacellar, Zachary Susskind, Mauricio Breternitz +4

We introduce the Differentiable Weightless Neural Network (DWN), a model based on interconnected lookup tables. Training of DWNs is enabled by a novel Extended Finite Difference te…