paper-with-me

Papers

Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models

2026-07-09 · Matteo Santelmo, Xiuying Wei, Israa Fakih, Felix Bauer, Juan Garcia Giraldo, Chengkun Li, Etienne Bamas, Emmanuel Abbé arxiv

Modern AI models achieve strong performance on many established benchmarks, yet they still fail on tasks that humans find almost trivial, such as manipulating a string or drawing a dog with five legs. These examples suggest that existing benchmarks may under-measure persistent blind spots in current systems. We introduce blind-spots-bench, a benchmark designed to expose such blind spots through tasks that appear simple for humans but remain challenging for modern AI. We collect raw questions from students in an AI course, clean and annotate them with structured reference solutions, and propose a task taxonomy tailored to the resulting dataset of 235 samples. We further develop an automated grading pipeline to evaluate a wide range of models, including open-weight and closed-source language, vision-language, and image-generation models. Our analysis on blind-spots-bench reveals that closed-source frontier models can substantially outperform open-weight models with even approx10% gap, even when they attain comparable performance on existing benchmarks. A more fine-grained analysis shows that no single model dominates across all task types, and that some tasks remain challenging for all evaluated models. These results highlight the value of blind-spots-bench as a diagnostic stress test for identifying concrete weaknesses in current modern models.

📄 PDF Abstract BibTeX arXiv:2607.08317

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Discovering Blind Spots in Reinforcement Learning

2018-05-23 · Ramya Ramakrishnan, Ece Kamar, Debadeepta Dey, Julie Shah 외

Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult to discover because the agent cannot predict the…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Towards a More Rigorous Science of Blindspot Discovery in Image Classification Models

2022-07-08 · Gregory Plumb, Nari Johnson, Ángel Alexander Cabrera, Ameet Talwalkar

A growing body of work studies Blindspot Discovery Methods ("BDM"s): methods that use an image embedding to find semantically meaningful (i.e., united by a human-understandable concept) subsets of the data where an image…

Dimensionality Reductionimage-classificationImage Classification

Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots

2022-03-14 · CVPR 2022 1 · Zejin Wang, Jiazheng Liu, Guoqing Li, Hua Han

Real noisy-clean pairs on a large scale are costly and difficult to obtain. Meanwhile, supervised denoisers trained on synthetic data perform poorly in practice. Self-supervised denoisers, which learn only from single no…

DenoisingImage Denoising

Methodological Blind Spots in Machine Learning Fairness: Lessons from the Philosophy of Science and Computer Science

2019-10-31 · Samuel Deng, Achille Varzi

In the ML fairness literature, there have been few investigations through the viewpoint of philosophy, a lens that encourages the critical evaluation of basic assumptions. The purpose of this paper is to use three ideas …

BIG-bench Machine LearningFairnessPhilosophy

Assessment of Vehicular Vision Obstruction Due to Driver-Side B-Pillar and Remediation with Blind Spot Eliminator

2023-02-08 · Dilara Baysal

Blind spots created by the driver-side B-pillar impair the ability of the driver to assess their surroundings accurately, significantly contributing to the frequency and severity of vehicular accidents. Vehicle manufactu…