# SAM 3: Segment Anything with Concepts

arXiv: https://arxiv.org/abs/2511.16719 · HTML: https://mlsanity.com/paper/2511.16719/

## Key facts

- Cited by 906 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2025.

## Built on by (most cited first, 30 of 906)

- [Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding](https://mlsanity.com/paper/2601.10611/) (2026)
- [CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation](https://mlsanity.com/paper/2603.22435/) (2026)
- [WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models](https://mlsanity.com/paper/2602.08971/) (2026)
- [Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception](https://mlsanity.com/paper/2602.11858/) (2026)
- [SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes](https://mlsanity.com/paper/2602.09153/) (2026)
- [HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds](https://mlsanity.com/paper/2604.14268/) (2026)
- [Image Generators are Generalist Vision Learners](https://mlsanity.com/paper/2604.20329/) (2026)
- [FireRed-Image-Edit-1.0 Technical Report](https://mlsanity.com/paper/2602.13344/) (2026)
- [Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance](https://mlsanity.com/paper/2603.02175/) (2026)
- [LLM-as-a-Verifier: A General-Purpose Verification Framework](https://mlsanity.com/paper/2607.05391/) (2026)
- [VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction](https://mlsanity.com/paper/2601.19887/) (2026)
- [LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models](https://mlsanity.com/paper/2603.07145/) (2026)
- [OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation](https://mlsanity.com/paper/2605.06481/) (2026)
- [OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning](https://mlsanity.com/paper/2603.24458/) (2026)
- [MedSAM3: Delving into Segment Anything with Medical Concepts](https://mlsanity.com/paper/2511.19046/) (2025)
- [Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation](https://mlsanity.com/paper/2601.10880/) (2026)
- [Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models](https://mlsanity.com/paper/2602.01166/) (2026)
- [RHO: Your Coding Agent is Secretly a Roboticist](https://mlsanity.com/paper/2606.16458/) (2026)
- [VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models](https://mlsanity.com/paper/2603.22003/) (2026)
- [SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning](https://mlsanity.com/paper/2606.13673/) (2026)
- [SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images](https://mlsanity.com/paper/2512.08730/) (2025)
- [MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models](https://mlsanity.com/paper/2606.13515/) (2026)
- [FlowWAM: Optical Flow as a Unified Action Representation for World Action Models](https://mlsanity.com/paper/2607.13017/) (2026)
- [MolmoPoint: Better Pointing for VLMs with Grounding Tokens](https://mlsanity.com/paper/2603.28069/) (2026)
- [EponaV2: Driving World Model with Comprehensive Future Reasoning](https://mlsanity.com/paper/2605.14696/) (2026)
- [Walk through Paintings: Egocentric World Models from Internet Priors](https://mlsanity.com/paper/2601.15284/) (2026)
- [EgoSim: Egocentric World Simulator for Embodied Interaction Generation](https://mlsanity.com/paper/2604.01001/) (2026)
- [Video Generation Models are General-Purpose Vision Learners](https://mlsanity.com/paper/2607.09024/) (2026)
- [Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning](https://mlsanity.com/paper/2608.27549/) (2026)
- [The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results](https://mlsanity.com/paper/2604.11998/) (2026)

## Abstract (arXiv)

We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short noun phrases (e.g., "yellow school bus"), image exemplars, or a combination of both. Promptable Concept Segmentation (PCS) takes such prompts and returns segmentation masks and unique identities for all matching object instances. To advance PCS, we build a scalable data engine that produces a high-quality dataset with 4M unique concept labels, including hard negatives, across images and videos. Our model consists of an image-level detector and a memory-based video tracker that share a single backbone. Recognition and localization are decoupled with a presence head, which boosts detection accuracy. SAM 3 doubles the accuracy of existing systems in both image and video PCS, and improves previous SAM capabilities on visual segmentation tasks. We open source SAM 3 along with our new Segment Anything with Concepts (SA-Co) benchmark for promptable concept segmentation.