SOURCE-LINKED INTELLIGENCE

Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

Multimodal reasoning requires models to draw on information from multiple modalities throughout the reasoning process. Yet existing methods often concatenate modality-specific thought tokens in a single sequence, leaving the model to bridge representational differences as it reasons across modalities. We introduce Uni-LaDiR (Unified Latent Diffusion Reasoner), a framework that brings these thoughts into a shared latent space for reasoning. A unified encoder maps teacher reasoning steps from different modalities into shared thought tokens, trained to preserve the information needed for later re

Read original source ↗ Open in workspace

recordType

paper

region

Global