Pith. sign in

REVIEW 5 cited by

Learning to Compose Neural Networks for Question Answering

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 1601.01705 v4 pith:36NYR47I submitted 2016-01-07 cs.CL cs.CVcs.NE

Jacob Andreas , Marcus Rohrbach , Trevor Darrell , Dan Klein This is my paper · ORCID
classification cs.CLcs.CVcs.NE
keywords modelneuralquestionansweringlearningmodulesnetworksparameters
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We describe a question answering model that applies to both images and structured knowledge bases. The model uses natural language strings to automatically assemble neural networks from a collection of composable modules. Parameters for these modules are learned jointly with network-assembly parameters via reinforcement learning, with only (world, question, answer) triples as supervision. Our approach, which we term a dynamic neural model network, achieves state-of-the-art results on benchmark datasets in both visual and structured domains.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios

    cs.LG 2024-11 conditional novelty 7.0 of 10

    A new attention-based reasoning module combining iterative steps with parallel operation slots improves accuracy on multiple visual question answering benchmarks while staying lightweight and partially interpretable.

  2. Language Model as Visual Explainer

    cs.CV 2024-12 reject novelty 6.0 of 10

    LVX builds LLM-generated attribute trees to explain any trained image classifier without training the explainer, but its faithfulness metric is directly optimized by the method.

  3. Mitigating Knowledge Conflicts in Language Model-Driven Question Answering

    cs.CL 2024-11 reject novelty 4.0 of 10

    On memorized question-answer pairs from KMIR and NQ, bottleneck and prefix adapters trained on entity-swapped contexts let a GPT-2 reader follow the new context most of the time, though no baselines are reported.

  4. Using Large Language Models for education managements in Vietnamese with low resources

    cs.CL 2025-01 reject novelty 3.0 of 10

    A framework that fine-tunes Bloom and Vistral on a synthetic Vietnamese educational-management QA dataset, with Vistral scoring higher but with no external baseline.

  5. A Comprehensive Survey on Visual Question Answering Datasets and Algorithms

    cs.CV 2024-11 unverdicted

    A broad but dated survey of VQA datasets and algorithms that organizes the pre-2021 literature into four dataset categories and six model paradigms.

Pith tools