Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression

Documenti analoghi

• MASA: Rethinking the Representational Bottleneck in LoRA with Multi-A Shared Adaptation
  di: Dong, Qin, et al.
  Pubblicazione: (2025)
• ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning
  di: Hu, Minda, et al.
  Pubblicazione: (2026)
• Can LLMs Reason Like Automated Theorem Provers for Rust Verification? VCoT-Bench: Evaluating via Verification Chain of Thought
  di: Xie, Zichen, et al.
  Pubblicazione: (2026)
• RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought
  di: Qiao, Junbo, et al.
  Pubblicazione: (2025)
• CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning
  di: Lin, Weihuang, et al.
  Pubblicazione: (2025)