Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals

Documenti analoghi

• Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives
  di: Wang, Qinsi, et al.
  Pubblicazione: (2025)
• FlashFPS: Efficient Farthest Point Sampling for Large-Scale Point Clouds via Pruning and Caching
  di: Fu, Yuzhe, et al.
  Pubblicazione: (2026)
• KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
  di: Ye, Hancheng, et al.
  Pubblicazione: (2025)
• HippoMM: Hippocampal-inspired Multimodal Memory for Long Audiovisual Event Understanding
  di: Lin, Yueqian, et al.
  Pubblicazione: (2025)
• CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models
  di: Wang, Qinsi, et al.
  Pubblicazione: (2025)