dayuwang401 /
spectral-orthogonal-exploration
Official code for "Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration" (SOE, ACL 2026 Oral). A training-free, test-time scaling method that fixes reasoning collapse in LLM mathematical reasoning via orthogonal probing.
Updated 15 min ago
Why now
+60 stars gained this week
3× its usual pace
Stars gained each day, last 30 days
Usual pace · 3 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
Runs on a vLLM-served stack with Python and needs a stronger Teacher and a weaker Student model; the README points to its own scripts for AIME, MATH-500 and similar benchmark evaluation.
Summary written by AI from the repository’s description and README.
dayuwang401 / spectral-orthogonal-exploration
View on GitHub(opens in new tab)