# Talking Points: Describing and Localizing Pixels

arXiv: https://arxiv.org/abs/2510.14583 · HTML: https://mlsanity.com/paper/2510.14583/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 34 of its 40 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 34)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [Ferret: Refer and Ground Anything Anywhere at Any Granularity](https://mlsanity.com/paper/2310.07704/) (2023)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [DeepPose: Human Pose Estimation via Deep Neural Networks](https://mlsanity.com/paper/1312.4659/) (2013)
- [GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest](https://mlsanity.com/paper/2307.03601/) (2023)
- [Semantic-SAM: Segment and Recognize Anything at Any Granularity](https://mlsanity.com/paper/2307.04767/) (2023)
- [RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback](https://mlsanity.com/paper/2402.03681/) (2024)
- [DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images](https://mlsanity.com/paper/1901.07973/) (2019)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding](https://mlsanity.com/paper/2406.19389/) (2024)
- [AP-10K: A Benchmark for Animal Pose Estimation in the Wild](https://mlsanity.com/paper/2108.12617/) (2021)
- [Cross-Domain Adaptation for Animal Pose Estimation](https://mlsanity.com/paper/1908.05806/) (2019)
- [PartImageNet: A Large, High-Quality Dataset of Parts](https://mlsanity.com/paper/2112.00933/) (2021)
- [Describe Anything: Detailed Localized Image and Video Captioning](https://mlsanity.com/paper/2504.16072/) (2025)
- [GROUNDHOG: Grounding Large Language Models to Holistic Segmentation](https://mlsanity.com/paper/2402.16846/) (2024)
- [Pose for Everything: Towards Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2207.10387/) (2022)
- [OV-PARTS: Towards Open-Vocabulary Part Segmentation](https://mlsanity.com/paper/2310.05107/) (2023)
- [CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose](https://mlsanity.com/paper/2206.11752/) (2022)
- [X-Pose: Detecting Any Keypoints](https://mlsanity.com/paper/2310.08530/) (2023)
- [Test-Time Reinforcement Learning for GUI Grounding via Region Consistency](https://mlsanity.com/paper/2508.05615/) (2025)

## Abstract (arXiv)

Vision-language models have achieved remarkable success in cross-modal understanding. Yet, these models remain limited to object-level or region-level grounding, lacking the capability for pixel-precise keypoint comprehension through natural language. We introduce a novel framework for pixel level grounding. The framework consists of two complementary components: a Point Descriptor that generates rich, contextual descriptions of individual keypoints, and a Point Localizer that regresses precise pixel coordinates from these descriptions. Unlike prior work that relies on templated prompts or keypoint names, our approach produces free-form, coarse-to-fine descriptions that situate keypoints within their visual context. Since there is no available dataset to train such a system, we introduce LlamaPointInPart, a carefully curated dataset of 20K+ image-keypoint-description triplets synthesized from multiple vision-language models, capturing multi-scale information from scene-level context to visual features around the keypoint. For cross-category generalization, we optimize the Point Descriptor on AP-10K via GRPO, using the frozen Point Localizer as a reward model to produce descriptions that maximize localization accuracy. To evaluate our results we establish a new evaluation protocol. Instead of comparing the text description produced by our method to the ground truth, we use the localizer to determine how close is the predicted point generated to the ground truth point. Experiments demonstrate superior performance compared to baseline models on LlamaPointInPart.The bidirectional nature of our framework should enable future applications in both keypoint-guided image understanding and language-guided precise localization. Our code and dataset are publicly available at https://github.com/matanr/Talking_Points.