OraCore · Topic ·research

TIDE distills diffusion LLMs across architectures

TIDE distills diffusion LLMs across architectures, adding noise-aware weighting and tokenizer-aware objectives to improve a 0.6B student.

1 articles in this thread ·Last updated 19h ago·First seen Jul 5, 2026

Timeline

  1. TIDE distills diffusion LLMs across architectures, adding noise-aware weighting and tokenizer-aware objectives to improve a 0.6B student.