XTC-Bench reveals that strong performance on generation or understanding tasks in unified multimodal models does not guarantee cross-task semantic consistency, which instead depends on how tightly coupled the learning objectives are across modalities.
Mme-unify: A comprehensive benchmark for unified multimodal understanding and generation models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 3polarities
background 3representative citing papers
Unified multimodal models exhibit pseudo-unification due to modality-asymmetric entropy encoding and pattern-split responses between text and image generation.
LatentRouter routes image-question queries to the best MLLM by predicting counterfactual performance via latent communication between learned query capsules and model capability tokens.
citing papers explorer
-
Beyond Accuracy: Benchmarking Cross-Task Consistency in Unified Multimodal Models
XTC-Bench reveals that strong performance on generation or understanding tasks in unified multimodal models does not guarantee cross-task semantic consistency, which instead depends on how tightly coupled the learning objectives are across modalities.
-
Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models
Unified multimodal models exhibit pseudo-unification due to modality-asymmetric entropy encoding and pattern-split responses between text and image generation.
-
LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?
LatentRouter routes image-question queries to the best MLLM by predicting counterfactual performance via latent communication between learned query capsules and model capability tokens.