Efficient VLM Training

VLM: Vision-Language Model

Follow this topic Ask about this topic

Latest papers

10 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

LightVLN: Efficient Aerial Vision-and-Language Navigation with Compact Memory and History-Guided Local Aggregation
Oct 4, 2026Yiming Zhao, Tianshun Li, Jingle He +2Memory-Augmented VLMs Vision-Language Models
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
V-REX: Efficient Specialist VLM Training for Veterinary X-Rays
Aug 20, 2026Tim Elsner, Nicole McNally, Andre Dourson +1Efficient VLM Training Vision-Language Models
Vyyo AI · Mars Petcare
Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training
Aug 14, 2026Hanfeng Lu, Tianyu Feng, Suyi Li +8Efficient VLM Training RL for VLMs
HKUST Hong Kong SAR · Alibaba Inc China
FlowTrain: Flow-Based Decoupled Training for Industrial-Grade Vision-Language Models
Jun 22, 2026Zhida Jiang, Zhaolong Xing, Yang Pei +14Vision-Language Models Efficient VLM Training
Huawei
On the Limits of Token Reduction for Efficient Unified Vision Language Training
May 31, 2026Siyi Chen, Weiming Zhuang, Jingtao Li +1Vision-Language Models Unified Multimodal Models
University of Michigan · Sony AI
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
May 20, 2026Dong Chen, Fangyun Wei, Ziyu Wan +18Multimodal Foundation Models T2I Diffusion Models
Microsoft Lens Team
ESsEN: Training Compact Discriminative Vision-Language Transformers in a Low-Resource Setting
Apr 20, 2026Clayton Fields, Casey KenningtonVision-Language Models Efficient ViTs
Department of Computer Science · Boise State University
EffiMiniVLM: A Compact Dual-Encoder Regression Framework
Apr 3, 2026Yin-Loon Khor, Yi-Jie Wong, Yan Chai HumMultimodal Regression Efficient VLM Training
Universiti Malaya, Kuala Lumpur 50603, Malaysia · Universiti Tunku Abdul Rahman, Selangor 43000, Malaysia
GreenRFM: Learning a resource-efficient radiology vision-language foundation model via supervision-centric pre-training
Mar 6, 2026Yingtai Li, Shuai Ming, Qiuli Wang +13Medical Imaging Foundation Models Radiology VLMs
School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China (USTC), Hefei, Anhui, 230026, China · Center for Medical Imaging, Robotics, Analytic Computing & Learning (MIRACLE), Suzhou Institute for Advanced Research, USTC, Suzhou, Jiangsu, 215123, China · Department of Radiology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, USTC, Hefei, Anhui, 230001, China +7
Parameter Efficient Multimodal Instruction Tuning for Romanian Vision Language Models
Dec 16, 2025George-Andrei Dima, Răzvan-Alexandru Smădu, Dumitru-Clementin CercelVLM Adaptation Image Captioning
National University of Science and Technology POLITEHNICA Bucharest, Bucharest, Romania

Oct 4, 2026J/K move · Enter open · S save

LightVLN: Efficient Aerial Vision-and-Language Navigation with Compact Memory and History-Guided Local Aggregation

Yiming Zhao, Tianshun Li, Jingle He, Ruonan Chai+1

The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China

Memory-Augmented VLMs Vision-Language Models UAV Navigation Vision-Language Navigation Efficient VLM Training Aerial VLN

Open paper AskPDF arXiv

Aerial vision-and-language navigation (VLN) enables unmanned aerial vehicles to execute long-horizon natural-language instructions from visual observations in complex three-dimensional environments. However, recent aerial VLN models often rely on large-scale vision-language backbones and dense visual histories, imposing substantial computation and memory costs that hinder onboard deployment. We propose LightVLN, a lightweight history-aware aerial VLN framework that combines a compact 0.5B language backbone with compact representations of both historical and current observations. LightVLN compresses each historical frame into a single token using visual features already computed by the policy. It further introduces history- and instruction-conditioned local aggregation to reduce the current observation from 256 to 32 visual tokens while preserving navigation-relevant spatial information. With up to 16 historical frames, the policy uses at most 48 observation-derived tokens. On the public OpenFly dataset, LightVLN achieves 50.93% Test-Seen and 36.14% Test-Unseen success rates (SR), outperforming the evaluated 7B language-backbone baselines on most reported metrics. It also achieves 25.83% SR on AerialVLN-S Val-Seen. In a reconstructed unseen campus, we deploy LightVLN on a DJI M350 RTK with an external Jetson Orin NX 16 GB for closed-loop onboard-compute real-to-sim hardware-in-the-loop (HIL) evaluation, achieving 14.61 Hz model inference and 11.13 Hz end-to-end decision updates. These results demonstrate the effectiveness and efficiency of LightVLN for aerial navigation.