Skip to content
Papers.

Segment Anything research paper by Meta, 2023

Meta · Apr 5, 2023 · Multimodal and robotics · 15,715 citations · 6 upvotes

Read on arXiv

What it shows

A promptable model and a dataset of over a billion masks that cut out any object in any image.

Summarised by hand from the abstract.

More from Meta

All 4
PaperCitations
Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and RecipesControlled experiments on when text, image understanding and image generation help or compete when trained together.Multimodal and robotics · Aug 20262
The Llama 3 Herd of ModelsOpen models up to 405B parameters that match leading closed models on many tasks.Foundation models · Jul 202418.8k
LLaMA: Open and Efficient Foundation Language ModelsOpen models from 7B to 65B trained only on public data; the 13B model beats GPT-3 on most benchmarks.Foundation models · Feb 202321.7k

Other multimodal and robotics papers

Topic
PaperCitations
Cosmos 3: Omnimodal World Models for Physical AIOne model that reads and generates text, images, video, audio and robot actions for physical AI.NVIDIA · Jun 202690
MolmoAct2: Action Reasoning Models for Real-world DeploymentA fully open robot action model, released with new datasets including 720 hours of two-arm teleoperation.Ai2 · May 202644
About this paper
Authors
Alexander Kirillov, Eric Mintun, Nikhila Ravi and 9 more
arXiv
2304.02643 · PDF
Venue
IEEE International Conference on Computer Vision
Citations
15,715, 2,053 influential · Semantic Scholar
Upvotes
6 · Hugging Face
Lab
Meta · on Companies · on Acquisitions · on Quarterly · on Paydays · on TechConf

Changes

What changed
New paperAdded to the listSep 24, 2026

Sources: each lab's own papers and arXiv, with citation and upvote counts from Semantic Scholar and Hugging Face. One-line summaries are for orientation, not a substitute for the paper. Logos via logo.dev; trademarks belong to their owners.

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.