activity
20172026
most citedStochastic Spiking Neural Networks Enabled by Magnetic Tunnel Junctions: From Nontelegraphic to Telegraphic Switching Regimes

79 citations · 135 across the 22 of their papers we have counts for

collaborators
Showing cs.NEShow all

12 papers · 1 filter

cs.NE2026

Neuromorphic Reinforcement Learning for Quadruped Locomotion Control on Uneven Terrain

Zhuangyu Han, Abhronil Sengupta

Reinforcement learning (RL) has enabled robust quadruped locomotion over complex terrain, but most learned controllers are trained offline with backpropagation in massively paralle…

cs.NE2026

RMAAT: Astrocyte-Inspired Memory Compression and Replay for Efficient Long-Context Transformers

Md Zesun Ahmed Mia, Malyaban Bal, Abhronil Sengupta

The quadratic complexity of self-attention mechanism presents a significant impediment to applying Transformer models to long sequences. This work explores computational principles…

cs.NE2025

Spatio-Temporal Pruning for Compressed Spiking Large Language Models

Yi Jiang, Malyaban Bal, Brian Matejek +3

Large Language Models (LLMs) present significant challenges for deployment in energy-constrained environments due to their large model sizes and high inference latency. Spiking Neu…

cs.NE2024

Scaling SNNs Trained Using Equilibrium Propagation to Convolutional Architectures

Jiaqi Lin, Malyaban Bal, Abhronil Sengupta

Equilibrium Propagation (EP) is a biologically plausible local learning algorithm initially developed for convergent recurrent neural networks (RNNs), where weight updates rely sol…

cs.NE2024

Exploring Extreme Quantization in Spiking Language Models

Malyaban Bal, Yi Jiang, Abhronil Sengupta

Despite the growing prevalence of large language model (LLM) architectures, a crucial concern persists regarding their energy and power consumption, which still lags far behind the…

cs.NE2024

P-SpikeSSM: Harnessing Probabilistic Spiking State Space Models for Long-Range Dependency Tasks

Malyaban Bal, Abhronil Sengupta

Spiking neural networks (SNNs) are posited as a computationally efficient and biologically plausible alternative to conventional neural architectures, with their core computational…