cd /news/artificial-intelligence/mosaic-adaptive-inter-layer-composit… · home topics artificial-intelligence article
[ARTICLE · art-56851] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models

Researchers propose MOSAIC, a hardware-aware search method that automatically transforms homogeneous vision-language models into optimized heterogeneous architectures by integrating diverse efficiency mechanisms. The resulting MOSAIC-4B model matches the performance of Qwen3-VL-4B-Instruct while requiring less than 2% of the original training cost and achieving significant inference speedups.

read1 min views1 publishedJul 13, 2026

arXiv:2607.09029v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have achieved success using homogeneous Transformers to process multimedia data. Recent studies show that heterogeneous structures interleaving efficient mechanisms, like linear attention, improve both performance and inference latency over homogeneous designs. However, these efforts rely on handcrafted static mixing patterns, which are sub-optimal and difficult to adapt to specific hardware. To bridge this gap, we propose Multi-Objective Search for Adaptive Inter-layer Composition (MOSAIC), a hardware-aware search method that automatically transforms homogeneous models into optimized heterogeneous architectures. MOSAIC integrates diverse efficiency mechanisms--including linear, sparse, and low-rank operators--into a unified search space. By formulating the selection as a multi-objective Mixed Integer Programming (MIP) problem, our method identifies optimal configurations that maximize downstream performance under strict hardware latency constraints. To mitigate performance degradation from structural transitions, we introduce a two-stage parameter recovery process: global off-policy distillation to stabilize internal representations, followed by a dual-teacher on-policy distillation leveraging a 235B oracle for knowledge expansion and the original 4B teacher for distributional stability. We validate MOSAIC through MOSAIC-4B, derived from Qwen3-VL-4B-Instruct. Results demonstrate that MOSAIC-4B matches the baseline's performance across multiple benchmarks while requiring less than 2% of the original training cost. Furthermore, it substantially improves inference efficiency, achieving 1.76x prefilling and 2.54x decoding speedups.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @mosaic 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/mosaic-adaptive-inte…] indexed:0 read:1min 2026-07-13 ·