The paper evaluates the claim that vision‑language models (VLMs) outperform task‑specific vision backbones for UAV power‑line defect assessment using the ElecVQA‑Bench benchmark. Across various evaluation settings—partitioning, item sets, label spaces, replication, resolution, and side information—the performance gap between VLMs and traditional backbones is minimal or even reversed when controlling for resolution and token budget. The study concludes that VLM superiority is not universally supported and emphasizes the importance of rigorous benchmark audits.
By Linghao Zhang, Siyu Xiang, Junwei Kuang, Peiyu Yi
arXiv:2609.05762v1 Announce Type: cross
Abstract: UAV image collections contain spatially and temporally related frames, yet semantic-segmentation benchmarks commonly split them at image level. Such...
By Tarek Rahman, Nazim-E-Alam, Md Kishor Morol, Jannatun Noor
arXiv:2609. 11916v1 Announce Type: new Abstract: Camera traps often run in the field on edge hardware with limited or no connectivity, making small, locally-deployable vision-language models (VLMs) -- not frontier-scale ones -- the practically relevant class to evaluate for species identification.
By William Zhou, Mayukha Siripuram, Xiao Yan, Ziqi Liu, Yi Ding
arXiv:2605. 20306v2 Announce Type: replace-cross Abstract: We introduce WildRoadBench, a wild aerial road-damage grounding benchmark that couples direct visual grounding by vision-language models with autonomous research-and-engineering by LLM-driven agents on a single professionally annotated UAV corpus.
By Bingnan Liu, Chenhang Cui, Rui Huang, Jiani Luo, Zhirong Shen, Tinghao Wang, Xiande Huang, Lingbei Meng, Fei Shen, An Zhang
VisionQ is a new benchmark for qualitative analysis in computer vision that evaluates vision‑language models (VLMs) on criterion‑conditioned visual discrimination. It is built from over 1,800 peer‑reviewed comparison figures in CVPR and ICCV papers, linking each image crop to author‑stated visual claims through 3,911 hand‑annotated data points. The benchmark includes a 51‑leaf taxonomy of visual criteria, a protocol that hides method identities and reports accuracy per criterion, and a DPO‑tuned Gemma‑4‑E4B judge that improves accuracy on a held‑out test set.
By Vu Dinh Xuan, Duc-Hai Nguyen, Minh-Dung Dao, Vu Quynh Giao, Quang Hong Nguyen, Binh-Son Hua, Barry O'Sullivan, David Murphy, Hoang D. Nguyen
arXiv:2609.18084v1 Announce Type: cross
Abstract: Fine-tuning a Vision-Language-Action (VLA) model for a new deployment environment is expensive, yet most methods apply uniform-capacity adapters to e...
By Shahram Najam Syed, Arthur Jakobsson, Prayuj Sachdev, Jeffrey Ichnowski
arXiv:2606. 08123v2 Announce Type: replace-cross Abstract: Model selection for safety-relevant visual recognition is often based on clean aggregate performance, although robustness, transfer, embedded latency, and explanation faithfulness may produce different preferences.
By Ruben Dario Florez-Zela
arXiv:2608.21762v1 Announce Type: cross
Abstract: Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image...
By Jinchang Zhu, Rong Fu, Yi Ding, Chenghao Wu, Ying Liu, Menglin Yang
arXiv:2609.00868v1 Announce Type: cross
Abstract: Vision-language models are evaluated by aggregate accuracy on multimodal benchmarks, a practice that implicitly assumes the model uses its visual inp...
By Genpei Zhang
arXiv:2608.08477v5 Announce Type: replace
Abstract: We build VectraYX-Vision-1B, a sub-2B Spanish/LATAM cybersecurity vision-language model for offline use, and measure what limits its visual groundi...
By Juan S. Santillana
arXiv:2607. 10826v1 Announce Type: cross Abstract: Automated evaluation is essential for scaling generative 3D systems, where exhaustive human review is costly and slow.
By Zhenyu Zhao, Nanshan Jia, Jihyeon Je, Yifu Tang, Alvin Chan, Michael Spedden, Michael V. Palleschi, Sui Huang, Jingshen Wang, Zeyu Zheng
The paper introduces RACO, a reliability‑aware adaptive coarse‑to‑fine navigation framework for inspection‑oriented UAV vision‑language navigation. It treats the coarse goal as a runtime hypothesis, using object‑level anchors to correct localization before and at the transition to the fine stage, and applies scale‑adaptive terminal refinement for near‑miss cases. RACO is evaluated on the new LG‑UVI inspection setting and outperforms the HETT baseline by 9.53 and 7.98 percentage points on validation‑unseen and test‑unseen, respectively, while improving inspection‑region arrival and reducing false verification risk.
By Sen Wang, Yiming Sun, Jiaxuan He, Pengfei Zhu