Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration

Documenti analoghi

• Beyond Static Cutoffs: One-Shot Dynamic Thresholding for Diffusion Language Models
  di: Shen, Jucheng, et al.
  Pubblicazione: (2025)
• On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention
  di: Ro, Yeonju, et al.
  Pubblicazione: (2025)
• SEAL: Steerable Reasoning Calibration of Large Language Models for Free
  di: Chen, Runjin, et al.
  Pubblicazione: (2025)
• LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models
  di: Sarah, Anthony, et al.
  Pubblicazione: (2024)
• Toward Scalable Video Narration: A Training-free Approach Using Multimodal Large Language Models
  di: Wu, Tz-Ying, et al.
  Pubblicazione: (2025)