Visual Programming: Compositional Visual Reasoning Without Training
CVPR'23, 2023. [All Versions]. VISPROG, a neuro-symbolic approach to solving complex and compositional visual tasks given natural language instructions, using the in-context learning ability of large language models to generate python-like modular programs, which are then…
- from
- AGI & CoCoSci
- added
- 2026-10-10
- likes
- 0
similar
-
Visual Concept Programming: A Visual Analytics Approach to Injecting Human Intelligence at Scale ieeexplore.ieee.org
IEEE Transactions on Visualization and Computer Graphics, 2023. [All Versions]. This paper presents Visual Concept Programming, a first-of-its-kind visual analytics approach of using visual concepts to program image data at scale while requiring a few human efforts.
-
Learning Compositional Rules via Neural Program Synthesis proceedings.neurips.cc
NeurIPS'20, 2020. [All Versions].
-
Neuro-Symbolic Visual Reasoning: Disentangling “Visual” from “Reasoning” arxiv.org
ICML'20, 2020. [All Versions].
-
Pragmatic Inference and Visual Abstraction Enable Contextual Flexibility During Visual Communication link.springer.com
Computational Brain & Behavior, 2020. [All Versions]. A computational account on the rational behavior in graphical language games.
-
A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs science.org
Science, 2017. [All Versions]. [Preprint]. Learning from a few examples and generalizing to markedly different situations are capabilities of human visual intelligence that are yet to be matched by leading machine learning models. By drawing inspiration from systems…
-
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision arxiv.org
ICLR'19, 2019. [All Versions].
AGI & CoCoSci › Papers > System 1 & System 2 > Neural-Symbolic AI: “CVPR'23, 2023. [All Versions]. VISPROG, a neuro-symbolic approach to solving complex and compositional visual tasks given natural language instructions, using the in-context learning ability of large language models to generate python-like modular programs, which are then…”