Do Unified Multimodal Models Think in One Space? A Lens Through Cross-Branch Steering

Transferability Between Understanding and Generation in Unified Multimodal Models

This work empirically finds that transferability depends on architecture-models with fully shared transformer backbone and a unified visual encoder exhibit consistent cross-task transfer, while loosely coupled designs show little or none.

Twins: Learn to Predict Unified Representations with Focal Loss

Twin, a unified continuous token space formed by channel-wise concatenating ViT and VAE features on the same token grid, so the sequence length is unchanged and attention cost does not increase is proposed, which performs competitively on multimodal understanding benchmarks and improves reconstruction fidelity.

When Does Visual Generation Help Visual Understanding in Unified Multimodal Models?

VGAU-Diag is introduced, a fine-grained evaluation framework for vision generation-assisted understanding that stratifies samples by difficulty, enables unified evaluation of multiple reasoning paradigms, and uses Oracle-Ass Reference Protocols.

A Model-Internal Protocol for Assessing Multimodal Models as Integrated Systems

As Large Vision-Language Models increasingly aim to integrate visual generation and understanding within a single parameter space, evaluating such structural unification in a cohesive manner remains a critical challenge. Current evaluation protocols predominantly treat generative and discriminative capabilities as separate tasks, leaving a gap in system-level evaluation for unified multimodal models (UMMs). In this work, we propose Self-Generative-Understanding (SGU), a novel, annotation-free evaluation framework that probes the integrated capabilities of unified models through a semantic closed-loop challenge. Without requiring new annotations, SGU leverages the dual understanding-and-generation abilities of UMMs by asking them to first perceive an image and produce a textual description, subsequently reconstruct a visual context based on that description, and finally perform reasoning over the self-generated output. This pipeline provides a zero-cost testbed that yields an integrated performance score specifically tailored for evaluating UMMs as unified systems. Extensive experiments show that even high-performing UMMs often struggle to reason over their own generated contexts, revealing limitations that are not captured by separate evaluations of understanding or generation alone. Our work provides a complementary holistic evaluation framework and offers a foundation for benchmarking the development of next-generation unified multimodal models.

SynthRGB-T: Language-Vision Guided Image Translation for Diversity Synthesis

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes

This study provides empirical clarity through a systematic exploration of multimodal pretraining and derives efficient pretraining recipes that achieve strong generative performance using only 5% of the compute budget.