Visual replay module and adaptive depth scaling improve multimodal latent reasoning, reaching SOTA benchmarks with faster inference than explicit chain-of-thought methods.
Llava-onevision: Easy visual task transfer
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Generation-to-Understanding synergy lets multimodal models create self-generated visual edits as intermediate steps, improving performance on twelve benchmarks while revealing limits in task-aligned self-reflection.
citing papers explorer
-
Visual Enhanced Depth Scaling for Multimodal Latent Reasoning
Visual replay module and adaptive depth scaling improve multimodal latent reasoning, reaching SOTA benchmarks with faster inference than explicit chain-of-thought methods.
-
Reversing the Flow: Generation-to-Understanding Synergy in Large Multimodal Models
Generation-to-Understanding synergy lets multimodal models create self-generated visual edits as intermediate steps, improving performance on twelve benchmarks while revealing limits in task-aligned self-reflection.