Accelerating Unified Multimodal Models with Core-Expansion Routing and Unified Computation Scheduling

arXiv:2608.29291v1 Announce Type: new Abstract: Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generation timesteps. Through token-importance probing, we identify an asymmetric core-expansion structure: understanding exhibits a stable importance component, while generation largely shares this component but requires progress-dependent corrections. We therefore propose CE-Router, which uses a task-shared core scorer and progress-conditioned generation expansions, optimized through generation decomposition and cross-task core alignment. At inference, CE-Router compacts token computation and supplies a learned routing signal to Unified Computation Scheduling, which coordinates layer skipping, FFN pruning, diffusion-head cache reuse, and denoising-step early exit. Experiments on two representative UMM architectures demonstrate consistent quality--efficiency improvements across both tasks, retaining 98.03% of dense understanding performance with a 1.93imes end-to-end inference speedup.

Related

• Where a New Concept Must Enter: Entry Point Gates Cross-Task Usability in Unified Multimodal Models
• Lance: Unified Multimodal Modeling by Multi-Task Synergy
• VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding

Source: arXiv cs.AI | 2026-09-01