Are VLMs Really Blind

Ayush Singh; Mansi Gupta; Shivank Garg

Are VLMs Really Blind

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.22029 v1 pith:KS2KBB76 submitted 2024-10-29 cs.CL cs.CV

Ayush Singh , Mansi Gupta , Shivank Garg This is my paper

classification cs.CLcs.CV

keywords modelsquestionblindcaptiongeometriclanguagereasoningtasks

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

Vision Language Models excel in handling a wide range of complex tasks, including Optical Character Recognition (OCR), Visual Question Answering (VQA), and advanced geometric reasoning. However, these models fail to perform well on low-level basic visual tasks which are especially easy for humans. Our goal in this work was to determine if these models are truly "blind" to geometric reasoning or if there are ways to enhance their capabilities in this area. Our work presents a novel automatic pipeline designed to extract key information from images in response to specific questions. Instead of just relying on direct VQA, we use question-derived keywords to create a caption that highlights important details in the image related to the question. This caption is then used by a language model to provide a precise answer to the question without requiring external fine-tuning.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

Image-Space Rule Discovery
cs.CV 2026-08 conditional novelty 6.0 of 10

A new benchmark shows frontier image-editing models can sometimes follow instructions rendered inside an image and answer on the same canvas, with the best model, Nano Banana Pro, reaching 48.7% strict proxy accuracy ...

Pith tools