跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1084新增论文
+883其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 19:45各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 05:08 — 2026-11-19 05:08(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45库内论文最新更新时间:2026-11-18 08:00

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

26,870 已收录论文22,374 AI 相关8,156 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 2 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
新论文 · v1arXiv:2611.14975

Aggregate Accuracy Hides Diagnosis-Specific Failure in Medical Vision-Language Models

Shreya Ajay Kale, Angad Ripudaman Singh Bajwa

原文摘要

Medical vision-language models (VLMs) are compared mainly by accuracy averaged across findings, a summary that can hide complete failure on a single diagnosis. We audit five open medical VLMs (MedGemma-4B, Lingshu-7B, HuatuoGPT-Vision-7B, Qwen2.5-VL-7B, and MedVLM-R1) on 6,048 ChestX-ray14 questions balanced by sex, age, finding, and label. On the 432 pneumothorax-positive X-rays, HuatuoGPT-Vision and Qwen2.5-VL detect zero cases while MedGemma and Lingshu detect 38% and 67% of the same images. The two failing models answer "no" to all 864 pneumothorax cases (balanced accuracy 0.500, chance), yet produce fluent, anatomically specific explanations that name the signs of a collapsed lung and then deny them, with no hedge or abstention. This failure is not an artifact of prompting, image resolution, label ambiguity, or model scale. It persists across four prompt formats, at native resolution, and on single-label cases. A within-model control shows the same forced prompt gives HuatuoGPT 79% recall on nodule but only 6% on pneumothorax. It survives a tenfold scale increase (Qwen2.5-VL-72B detects 4%) and replicates on SIIM-ACR, an independent dataset with radiologist-drawn masks, where the failing models detect 0 of 432 confirmed pneumothoraces, including 0 of the 144 largest lesions. Reading the models' logits and internal states shows this is not blindness. The two failing models are highly confident yet no better than chance and a linear probe recovers pneumothorax from their hidden representations even where recall is zero, so the finding is represented internally but suppressed at the output. Aggregate accuracy therefore cannot establish that a medical VLM can see a given finding, because a model that misses one can still describe it convincingly. Reporting per-finding recall and specificity on balanced cases is needed to tell the difference.

eess.IV · cs.CL · cs.CV · cs.LG

新论文 · v1arXiv:2611.13774

AI-Adaptive Virtual Reality for STEM: Engagement, Retention, and Learning Outcomes

Srinivasa K G, Akshit Rana, Aman Singh, Kshitij Kumar Singh Chauhan

原文摘要

Virtual Reality (VR) presents a com pelling opportunity to transform STEM pedagogy; however, empirical evidence evaluating AI-driven adaptivity, objective engagement metrics, and long-term knowledge retention remains sparse. This paper proposes and evaluates an AI-adaptive VR based solar system learning module deployed on Meta Quest 2, wherein a machine learning model dynamically adjusts in structional difficulty based on real-time learner interaction logs including dwell time, gaze patterns, and response latency. A controlled between-subjects experiment was conducted involving 120 secondary school students (mean age 14.3 years) across three schools in India, randomly assigned to three conditions: AI adaptive VR, standard VR, and traditional classroom instruction. Engagement was measured objectively through eye-tracking fixation density and heart rate variability (HRV), alongside pre-test, immediate post-test, and delayed post-tests at one week and one month intervals. Statistical analyses encompassing paired t-tests, one-way ANOVA, and Structural Equation Modeling (SEM) reveal that the AI-adaptive VR cohort demonstrated significantly higher knowledge improvement scores (mean gain = 38.4 vs. 31.2 vs. 10.7), superior one-month retention (p < 0.001), and measurably elevated engagement across all biometric indicators. SEM confirmed immersion as a significant mediator between adaptive instruction and knowledge acquisition (\b{eta} = 0.63, p < 0.001). Post-session self-directed learning exploration was recorded at 80% among AI-adaptive VR participants versus 40% in the traditional group. These findings establish an evidence based framework for deploying AI-adaptive immersive learning environments in resource-varied STEM educational contexts.

cs.ET