DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning

Documenti analoghi

• PQCache: Product Quantization-based KVCache for Long Context LLM Inference
  di: Zhang, Hailin, et al.
  Pubblicazione: (2024)
• Galvatron: An Automatic Distributed System for Efficient Foundation Model Training
  di: Liu, Xinyi, et al.
  Pubblicazione: (2025)
• Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion Inference
  di: Yu, Zihao, et al.
  Pubblicazione: (2023)
• SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling
  di: Ji, Xiaodong, et al.
  Pubblicazione: (2025)
• Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
  di: Xu, Yixuan Even, et al.
  Pubblicazione: (2025)