Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention

Documenti analoghi

• DATA: Decomposed Attention-based Task Adaptation for Rehearsal-Free Continual Learning
  di: Liao, Huanxuan, et al.
  Pubblicazione: (2025)
• Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks
  di: Liao, Huanxuan, et al.
  Pubblicazione: (2024)
• Shuttle Between the Instructions and the Parameters of Large Language Models
  di: Sun, Wangtao, et al.
  Pubblicazione: (2025)
• Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement
  di: Tan, Yuqiao, et al.
  Pubblicazione: (2025)
• Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering
  di: Liao, Huanxuan, et al.
  Pubblicazione: (2024)