VAPO: End-to-end Slide-Enhanced Speech Recognition with Omni-modal Large Language Models

Unisound 7

Faithful rendering of page 1 from ACL2026_VAPO.pdf

Faithful rendering of page 2 from ACL2026_VAPO.pdf

Faithful rendering of page 3 from ACL2026_VAPO.pdf

Faithful rendering of page 4 from ACL2026_VAPO.pdf

Faithful rendering of page 5 from ACL2026_VAPO.pdf

Faithful rendering of page 6 from ACL2026_VAPO.pdf

Faithful rendering of page 7 from ACL2026_VAPO.pdf

Faithful rendering of page 8 from ACL2026_VAPO.pdf

Faithful rendering of page 9 from ACL2026_VAPO.pdf

Faithful rendering of page 10 from ACL2026_VAPO.pdf

Faithful rendering of page 11 from ACL2026_VAPO.pdf

Faithful rendering of page 12 from ACL2026_VAPO.pdf

Faithful rendering of page 13 from ACL2026_VAPO.pdf

Faithful rendering of page 14 from ACL2026_VAPO.pdf

Faithful rendering of page 15 from ACL2026_VAPO.pdf

Faithful rendering of page 16 from ACL2026_VAPO.pdf