# Jev Visual

Educational MLX/Qwen vision-language experiment sharing image context across candidate-scoring questions; its probabilities are not calibrated correctness estimates.

Source: https://github.com/hr98w/jev-visual

Category: Open reproductions and research

Snapshot: 2026-09-19. Inclusion is not an endorsement.

- cobanov/awesome-jev: https://github.com/cobanov/awesome-jev/blob/ef507d7935aeac9240d4e68c8d0392ad11aa4122/README.md#L180