Hugging Face Papers ↗ · 2026-11-19
Suppressing the Shortcut Hidden Behind the Gains of VideoLLM Fine-Tuning
Media reports Hugging Face Papers Source language: Chinese
VETO projects supervised fine‑tuning updates onto the orthogonal complement of the text‑only activation subspace, suppressing shortcut learning in VideoLLMs. This improves out‑of‑distribution video reasoning performance.
Full text
VETO suppresses shortcut learning in VideoLLMs by projecting supervised fine-tuning updates onto the orthogonal complement of the text-only activation subspace, improving out-of-distribution video reasoning.