UniVLR unifies textual and visual reasoning in multimodal LLMs by compressing reasoning traces and auxiliary images into visual latent tokens for direct inference without interleaved text CoT.
As outlined in Algorithm 1, the canvas width is constrained by a minimum threshold and the scaled auxiliary image
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
UniVLR unifies textual and visual reasoning in multimodal LLMs by compressing reasoning traces and auxiliary images into visual latent tokens for direct inference without interleaved text CoT.