Modeling sparse visual state updates instead of full images cuts generated visual tokens ~55.6% and improves interleaved multimodal reasoning over full-image ULMMs.
International Journal of Computer Vision , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
CONDITIONAL 2representative citing papers
Audex unifies audio understanding and generation on a strong text MoE backbone with multi-stage SFT plus text-only Cascade RL, matching open SOTA audio scores while mostly retaining text capability.
citing papers explorer
-
DeltaV: Thinking with Visual State Updates in Unified Large Multimodal Models
Modeling sparse visual state updates instead of full images cuts generated visual tokens ~55.6% and improves interleaved multimodal reasoning over full-image ULMMs.
-
Unified Audio Intelligence Without Regressing on Text Intelligence
Audex unifies audio understanding and generation on a strong text MoE backbone with multi-stage SFT plus text-only Cascade RL, matching open SOTA audio scores while mostly retaining text capability.