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.
arXiv:2605.31351v2 Announce Type: replace-cross Abstract: AI-based Visually Impaired Assistance (VIA) remains challenging, largely due to the high cost of human evaluation. The VLM-as-a-Judge paradig...
arXiv:2609.09417v1 Announce Type: new Abstract: Vision-language models (VLMs) show promise for agricultural classification, but zero-shot performance on disease, pest, damage, quality, and species id...
arXiv:2606. 18451v1 Announce Type: new Abstract: Single-image-to-3D generators are improving quickly, but there is no agreed, human-free way to tell whether one generated mesh is better than another.
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...
arXiv:2609. 31450v1 Announce Type: cross Abstract: Medical vision-language model (VLM) post-training is commonly evaluated through answer accuracy.
arXiv:2603. 09715v2 Announce Type: replace Abstract: Visual instruction tuning is crucial for improving vision-language large models (VLLMs).
arXiv:2606. 16082v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have been increasingly adopted for Image Quality Assessment (IQA).
arXiv:2607. 16311v1 Announce Type: cross Abstract: Vision-language models (VLMs) often answer visual questions using learned language and category priors rather than grounding their predictions in the image itself.
The paper introduces a dual‑judge evaluation protocol for vision‑language models in legally grounded tasks, pairing a 0‑10 quality judge with a strict binary semantic‑equivalence judge. Using a controlled UK traffic‑sign interpretation task, the authors analyze 4,680 evaluations across visibility and occlusion conditions, finding moderate association between judges and an asymmetric Type II error pattern that is most pronounced under heavy occlusion. The protocol requires only one additional LLM call and reveals quality‑trustworthiness signals that single‑judge methods miss.
The paper introduces CompareBench, a new benchmark suite for evaluating visual comparison reasoning in vision‑language models. It includes TallyBench for object counting, OmniCaps for captioning and tagging, and a 1,200‑question CompareBench that tests quantity, geometric, spatial, and temporal comparisons. Experiments on nine closed‑source models show strong overall performance but persistent weaknesses in counting, spatial reasoning, geometric comparison, and temporal ordering, highlighting visual comparison as a systematic challenge for current VLMs.
arXiv:2607. 06254v1 Announce Type: cross Abstract: Deepfake image detection is currently served by three fundamentally different paradigms: commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors.
arXiv:2609.32352v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) have shown increasing potential for medical image understanding, yet their capabilities in ophthalmic imaging r...