Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
SAGE: Surrogate-gradient Adaptation via Attention-Guided Entropy for Spiking Transformers
Kiran Nair, Rodrigue Rizk, KC Santosh
Spiking neural networks (SNNs) offer an energy-efficient alternative to conventional deep neural networks by exploiting sparse event-driven computation, but their training remains…
cs.LG2026
Uncertainty-Aware LLM-Guided Policy Shaping for Sparse-Reward Reinforcement Learning
Ujjwal Bhatta, Utsabi Dangol, Sumaly Bajracharya +2
Sparse rewards and heterogeneous task sequences remain persistent challenges in Reinforcement Learning (RL), often resulting in slow convergence, weak generalization, and inefficie…