Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models

Documenti analoghi

• Aligning Large Language Models with Searcher Preferences
  di: Wu, Wei, et al.
  Pubblicazione: (2026)
• TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
  di: Wu, Wei, et al.
  Pubblicazione: (2024)
• Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints
  di: Yang, Dongjie, et al.
  Pubblicazione: (2025)
• RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
  di: Zhang, Rongyang, et al.
  Pubblicazione: (2025)
• RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios
  di: Zhao, Fei, et al.
  Pubblicazione: (2025)