Understanding and Enhancing the Planning Capability of Language Models via Multi-Token Prediction

Documenti analoghi

• Toward Consistent World Models with Multi-Token Prediction and Latent Semantic Enhancement
  di: Zhong, Qimin, et al.
  Pubblicazione: (2026)
• Exploring Loss Landscapes through the Lens of Spin Glass Theory
  di: Liao, Hao, et al.
  Pubblicazione: (2024)
• ALPINE: Unveiling the Planning Capability of Autoregressive Learning in Language Models
  di: Wang, Siwei, et al.
  Pubblicazione: (2024)
• How Transformers Learn to Plan via Multi-Token Prediction
  di: Huang, Jianhao, et al.
  Pubblicazione: (2026)
• Fine-Tuning Medical Language Models for Enhanced Long-Contextual Understanding and Domain Expertise
  di: Yang, Qimin, et al.
  Pubblicazione: (2024)