Latent visual reasoning improves multimodal models via training effects even without using latent tokens at inference, enabled by an attention-based RL reward that promotes interaction with text tokens.
Visual sketchpad: Sketching as a visual chain of thought for multimodal language models.Advances in Neural Information Processing Systems, 37:139348–139379,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Leveraging Latent Visual Reasoning in Silence
Latent visual reasoning improves multimodal models via training effects even without using latent tokens at inference, enabled by an attention-based RL reward that promotes interaction with text tokens.