ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models

Documenti analoghi

• Enhancing Transformer RNNs with Multiple Temporal Perspectives
  di: Dumitru, Razvan-Gabriel, et al.
  Pubblicazione: (2024)
• Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy
  di: Dumitru, Razvan-Gabriel, et al.
  Pubblicazione: (2024)
• CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality
  di: Dumitru, Razvan-Gabriel, et al.
  Pubblicazione: (2025)
• Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels
  di: Dumitru, Razvan-Gabriel, et al.
  Pubblicazione: (2024)
• ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration
  di: Deng, Minghang, et al.
  Pubblicazione: (2025)