Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models
Reinforcement learning approaches for improving LLM reasoning capabilities are enhanced by a Bayesian Manifold Curriculum framework that structures problem sampling based on task m…
Hugging Face · Daily Papers
·Darrien McKenzie, Nicklas Hansen
·
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Darrien McKenzie, Nicklas Hansen, Xiaolong Wang
- 0 upvotes da comunidade
- Temas: reinforcement learning, large language models, adaptive curriculum learning, bandit problem, manifold-structured bandit, endogenous non-stationarity
Resumo
Resumo original (em inglês), extraído do paper:
Reinforcement learning approaches for improving LLM reasoning capabilities are enhanced by a Bayesian Manifold Curriculum framework that structures problem sampling based on task manifold relationships and endogenous non-stationarity.
