arXiv Computer Vision
Target-Checked Reliability Score Refinement for Video Question Answering
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 10
Evidence-Order Calibration for Selective Visual Reasoning under Progressive Loss of Question-Critical Evidence
arXiv:2609.09184v1 Announce Type: new Abstract: Vision-language model (VLM) confidence may change in aggregate when visual evidence is degraded while remaining structurally inconsistent within indivi...
arXiv Computation and Language
Oct 27
Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification
arXiv:2605.00326v2 Announce Type: replace Abstract: Safety pipelines often block content by thresholding a model's first-token unsafe score. We show that a single prompt's score is not a reliable pro...
arXiv AI
Sep 28
From Reward Signal to Visual Utility: A Controlled Audit of Medical VLM Post-Training
arXiv:2609. 31450v1 Announce Type: cross Abstract: Medical vision-language model (VLM) post-training is commonly evaluated through answer accuracy.
arXiv Computer Vision
Sep 15
Vision-Language Models for Criterion-Level Grading of Handwritten Examinations in Outcome-Based Education
arXiv:2609.14284v1 Announce Type: new Abstract: Criterion-level grading connects examination performance to learning outcomes, but manual marking introduces workload and variation between markers. Th...
arXiv AI
Oct 2
VisionQ: VLM-as-a-Judge Taxonomy, Dataset and Benchmark for Qualitative Analysis in Computer Vision
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 Computer Vision
Oct 5
Behavior Pack Optimization for Video MLLM Post-Training
The paper introduces Behavior Pack Optimization (BPO), a post‑training method for video multimodal large language models that replaces single‑response rewards with a set of outputs across counterfactual views. BPO enforces stability when interventions are irrelevant, sensitivity when key evidence is removed, and abstention when no evidence remains, using an anchor‑relative advantage to keep the objective stable with small pack sizes. Experiments on datasets such as TempCompass, MVBench, and NExT‑QA show that BPO improves macro accuracy and abstention metrics for models like Qwen2.5‑VL‑7B‑Instruct, with gains that transfer to other benchmarks and models.