Latency and Token-Aware Test-Time Compute

Documenti analoghi

• Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
  di: Damani, Mehul, et al.
  Pubblicazione: (2024)
• The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
  di: Akyürek, Ekin, et al.
  Pubblicazione: (2024)
• Vector Policy Optimization: Training for Diversity Improves Test-Time Search
  di: Bahlous-Boldi, Ryan, et al.
  Pubblicazione: (2026)
• Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models
  di: Puri, Isha, et al.
  Pubblicazione: (2026)
• Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
  di: Damani, Mehul, et al.
  Pubblicazione: (2025)