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