Pith. sign in

REVIEW 4 cited by

Modular Visual Question Answering via Code Generation

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 2306.05392 v1 pith:KCVMSXF4 submitted 2023-06-08 cs.CL

Sanjay Subramanian , Medhini Narasimhan , Kushal Khangaonkar , Kevin Yang , Arsha Nagrani , Cordelia Schmid , Andy Zeng , Trevor Darrell
show 1 more author
Dan Klein
This is my paper
classification cs.CL
keywords visualcodegenerationmodelsmodularansweringapproachdataset
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present a framework that formulates visual question answering as modular code generation. In contrast to prior work on modular approaches to VQA, our approach requires no additional training and relies on pre-trained language models (LMs), visual models pre-trained on image-caption pairs, and fifty VQA examples used for in-context learning. The generated Python programs invoke and compose the outputs of the visual models using arithmetic and conditional logic. Our approach improves accuracy on the COVR dataset by at least 3% and on the GQA dataset by roughly 2% compared to the few-shot baseline that does not employ code generation.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning

    cs.CV 2026-01 conditional novelty 7.0 of 10

    VIGA introduces a training-free interleaved multimodal reasoning loop that improves vision-as-inverse-graphics accuracy over one-shot baselines on BlenderGym, SlideBench, and new BlenderBench.

  2. Visual Programmability: A Guide for Code-as-Thought in Chart Understanding

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A vision-language model learns to dynamically switch between code-based and visual reasoning for chart questions, improving average accuracy by about one point over fixed strategies.

  3. CountGD++: Generalized Prompting for Open-World Counting

    cs.CV 2025-12 conditional novelty 5.0 of 10

    Counting with negative prompts, auto-generated exemplars, and external or synthetic example images improves accuracy across seven open-world counting benchmarks.

  4. Augmented Vision-Language Models: A Systematic Review

    cs.CL 2025-07 conditional novelty 5.0 of 10

    A structured taxonomy of inference-time augmentation techniques that connect vision-language models to external symbolic systems, tools, and knowledge sources.

Pith tools