# PinPoint: Prompting with Informative Interior Points

arXiv: https://arxiv.org/abs/2605.26689 · HTML: https://mlsanity.com/paper/2605.26689/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 31 of its 38 references that are in the map.
- First posted on arXiv 26 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 31)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [GRES: Generalized Referring Expression Segmentation](https://mlsanity.com/paper/2306.00968/) (2023)
- [Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement](https://mlsanity.com/paper/2503.06520/) (2025)
- [PixelLM: Pixel Reasoning with Large Multimodal Model](https://mlsanity.com/paper/2312.02228/) (2023)
- [Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos](https://mlsanity.com/paper/2501.04001/) (2025)
- [GSVA: Generalized Segmentation via Multimodal Large Language Models](https://mlsanity.com/paper/2312.10103/) (2023)
- [VISA: Reasoning Video Object Segmentation via Large Language Models](https://mlsanity.com/paper/2407.11325/) (2024)
- [SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation](https://mlsanity.com/paper/2409.10542/) (2024)
- [PerceptionGPT: Effectively Fusing Visual Perception into LLM](https://mlsanity.com/paper/2311.06612/) (2023)
- [Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Models](https://mlsanity.com/paper/2405.02917/) (2024)
- [Calibrating the Confidence of Large Language Models by Eliciting Fidelity](https://mlsanity.com/paper/2404.02655/) (2024)
- [SAMAug: Point Prompt Augmentation for Segment Anything Model](https://mlsanity.com/paper/2307.01187/) (2023)
- [SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning](https://mlsanity.com/paper/2505.22596/) (2025)
- [UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning](https://mlsanity.com/paper/2509.18094/) (2025)
- [IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis](https://mlsanity.com/paper/2503.00936/) (2025)
- [LENS: Learning to Segment Anything with Unified Reinforced Reasoning](https://mlsanity.com/paper/2508.14153/) (2025)
- [CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos](https://mlsanity.com/paper/2505.18561/) (2025)
- [Stable Segment Anything Model](https://mlsanity.com/paper/2311.15776/) (2023)
- [Quantifying the Limits of Segmentation Foundation Models: Modeling Challenges in Segmenting Tree-Like and Low-Contrast Objects](https://mlsanity.com/paper/2412.04243/) (2024)
- [RESAnything: Attribute Prompting for Arbitrary Referring Segmentation](https://mlsanity.com/paper/2505.02867/) (2025)

## Abstract (arXiv)

Modern referring image segmentation pipelines couple a vision-language model (VLM) for grounding with a promptable segmenter such as the Segment Anything Model (SAM) for mask generation. Prior training-free instances of this recipe consistently trail fine-tuned and reinforcement-learning (RL)-tuned specialists, and it has been unclear whether the gap comes from the VLM's grounding, SAM's capacity, or the prompt. We show that the gap is dominated by prompt ambiguity: a VLM-proposed bounding box (bbox) leaves SAM to guess which pixels inside the bbox belong to the object the expression denotes. Interior points are the natural disambiguator, but where they fall matters; prior work relies on naively sampled points that land on boundaries, distractors, and background clutter, and can even hurt performance compared to the bbox alone. Supervised and RL-tuned methods close this gap by training a VLM to predict better points; we show that this training is unnecessary. At a matched budget of five interior points, replacing naive sampling with stable, informative point selection improves cumulative Intersection-over-Union (cIoU) by 12-18 points across RefCOCO/+/g, with every model fixed. We turn this observation into PinPoint, a deterministic, training-free point selector that fuses four visual cues into a consensus map, selects compact, spatially diverse points away from boundaries, and uses the frozen VLM to label each point. Without any task-specific training, PinPoint matches supervised and RL-tuned specialists on the same stack while issuing only two VLM calls per query.