SIMIT Enables Label-Free Test-Time Self-Improvement for VLMs

Researchers from DTU and others proposed SIMIT, which lets vision-language models self-improve at test time with zero labels by imagining practice questions before answering, achieving an average 7.2% gain across 17 benchmarks.

2026-10-28 ~ 2026-10-28 · 2 related posts

• SIMIT: VLMs self-improve at test time by imagining practice problems, +7.2% on 17 benchmarks — delliott · 2026-10-28
• SIMIT lets vision-language models self-improve at test time, +7.2% across 17 benchmarks — aykuterdemml · 2026-10-28