When More Data Hurts: Optimizing Data Coverage While Mitigating Diversity Induced Underfitting in an Ultra-Fast Machine-Learned Potential

Documenti analoghi

• When More Experts Hurt: Underfitting in Multi-Expert Learning to Defer
  di: Liu, Shuqi, et al.
  Pubblicazione: (2026)
• Accelerating superconductor discovery through tempered deep learning of the electron-phonon spectral function
  di: Gibson, Jason B., et al.
  Pubblicazione: (2024)
• Enhancing Document-Level Machine Translation via Filtered Synthetic Corpora and Two-Stage LLM Adaptation
  di: Kim, Ireh, et al.
  Pubblicazione: (2026)
• Selective Underfitting in Diffusion Models
  di: Song, Kiwhan, et al.
  Pubblicazione: (2025)
• When More Retrieval Hurts: Retrieval-Augmented Code Review Generation
  di: Meng, Qianru, et al.
  Pubblicazione: (2025)