CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models

Documenti analoghi

• Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs Can Analyze Long Sequences Flawlessly
  di: Hosseini, Peyman, et al.
  Pubblicazione: (2024)
• Cost-Effective Attention Mechanisms for Low Resource Settings: Necessity & Sufficiency of Linear Transformations
  di: Hosseini, Peyman, et al.
  Pubblicazione: (2024)
• Lon-ea at SemEval-2023 Task 11: A Comparison of Activation Functions for Soft and Hard Label Prediction
  di: Hosseini, Peyman, et al.
  Pubblicazione: (2023)
• PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialogues
  di: Kajare, Prajwal Vijay, et al.
  Pubblicazione: (2026)
• Clustering-driven Memory Compression for On-device Large Language Models
  di: Bohdal, Ondrej, et al.
  Pubblicazione: (2026)