4 papers
Recurrent Modular Structure in Spiking Neural Network Reinforcement Learning
Vikram Ramavarapu, Himanshu Udupi, Ashish Gautam
Biological neural circuits are both modular and recurrent, with dense communities sparsely linked to one another. Spiking neural networks (SNNs) for reinforcement learning are usua…
Skip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files
Xiaocong Yang, Rishit Chatterjee, Himanshu Udupi +2
A coding agent works on repositories that can be far larger than its context window can hold. Prompt compressors and retrievers offer solutions to this problem, but patching an iss…
Convex Optimization of Spiking Neural Networks with Global and Approximation Guarantees
Himanshu Udupi, Xiaocong Yang, Calvin Ang +2
Spiking neural networks (SNNs) have been proposed as energy-efficient alternatives to deep neural networks. Their training is non-convex and involves a non-differentiable spike fun…
zScore: A Universal Decentralised Reputation System for the Blockchain Economy
Himanshu Udupi, Ashutosh Sahoo, Akshay S. P. +3
Modern society functions on trust. The onchain economy, however, is built on the founding principles of trustless peer-to-peer interactions in an adversarial environment without a…