3 papers
cs.LG2026
Evolution Strategies for Deep RL pretraining
Adrian MartÃnez, Ananya Gupta, Hanka Goralija +3
Although Deep Reinforcement Learning has proven highly effective for complex decision-making problems, it demands significant computational resources and careful parameter adjustme…
cs.LG2025
Overcoming catastrophic forgetting in neural networks
Brandon Shuen Yi Loke, Filippo Quadri, Gabriel Vivanco +2
Catastrophic forgetting is the primary challenge that hinders continual learning, which refers to a neural network ability to sequentially learn multiple tasks while retaining prev…
cs.CL2025
From BERT to Qwen: Hate Detection across architectures
Ariadna Mon, Saúl Fenollosa, Jon Lecumberri
Online platforms struggle to curb hate speech without over-censoring legitimate discourse. Early bidirectional transformer encoders made big strides, but the arrival of ultra-large…