AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

mVLM: A Vision Language Model for mNPUs

Zijie Chen, Guiyun Fan, Zhaoxing Yang, Rong Ding, Haiming Jin

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add dynamic ED blocks to OverMod encoder (ablation)OverMod · ImageNet-1K valtop-1 accuracy (%): 75.8 -> 77.6Improved
add Dilated RepConv to OverMod (ablation)OverMod · ImageNet-1K valtop-1 accuracy (%): 77.6 -> 78.4Improved
add GRN to OverMod (ablation)OverMod · ImageNet-1K valtop-1 accuracy (%): 78.4 -> 78.9Improved
add Layer Scale to OverMod (ablation)OverMod · ImageNet-1K valtop-1 accuracy (%): 78.9 -> 79.2Improved
add SE module to OverNet or ModNet encoder (ablation)OverMod · ImageNet-1K valtop-1 accuracy (%): 79.2 -> 79.0Hurt
add dynamic convolution (ablation)µVLM · COCO Karpathy testCIDEr: 95.5 -> 101.4Improved
add multi-scale feature fusion (ablation)µVLM · COCO Karpathy testCIDEr: 101.4 -> 107.1Improved
add spatial modulation in decoder attention (ablation)µVLM · COCO Karpathy testCIDEr: 107.1 -> 115.2Improved
add channel modulation in decoder attention (ablation)µVLM · COCO Karpathy testCIDEr: 115.2 -> 117.8Improved
replace LSTM with Bahdanau attention by AttSSM decoder (ablation)µVLM on STM32N657 · on-device latencylatency (ms): 32 -> 21Improved
scale OverMod from tiny to baseµVLM · COCO Karpathy testCIDEr: 96.4 -> 117.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy