Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Evo: Autoregressive-Diffusion Large Language Models with Evolving Balance
Junde Wu, Minhao Hu, Jiayuan Zhu +7
We introduce \textbf{Evo}, a duality latent trajectory model that bridges autoregressive (AR) and diffusion-based language generation within a continuous evolutionary generative fr…
cs.LG2025
Generalization and Optimization of SGD with Lookahead
Kangcheng Li, Yunwen Lei
The Lookahead optimizer enhances deep learning models by employing a dual-weight update mechanism, which has been shown to improve the performance of underlying optimizers such as…