# PoseLLM: Enhancing Language-Guided Human Pose Estimation with MLP Alignment

arXiv: https://arxiv.org/abs/2507.09139 · HTML: https://mlsanity.com/paper/2507.09139/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 12 Jul 2025.

## Builds on (most cited first, 23 of 23)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)
- [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)
- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues](https://mlsanity.com/paper/2412.15190/) (2024)
- [SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation](https://mlsanity.com/paper/2107.03332/) (2021)
- [Human-Art: A Versatile Human-Centric Dataset Bridging Natural and Artificial Scenes](https://mlsanity.com/paper/2303.02760/) (2023)
- [LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model](https://mlsanity.com/paper/2406.04659/) (2024)
- [Markerless human pose estimation for biomedical applications: a survey](https://mlsanity.com/paper/2308.00519/) (2023)
- [TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splatting](https://mlsanity.com/paper/2503.17032/) (2025)
- [Keypoint-Integrated Instruction-Following Data Generation for Enhanced Human Pose and Action Understanding in Multimodal Models](https://mlsanity.com/paper/2409.09306/) (2024)

## Abstract (arXiv)

Human pose estimation traditionally relies on architectures that encode keypoint priors, limiting their generalization to novel poses or unseen keypoints. Recent language-guided approaches like LocLLM reformulate keypoint localization as a vision-language task, enabling zero-shot generalization through textual descriptions. However, LocLLM's linear projector fails to capture complex spatial-textual interactions critical for high-precision localization. To address this, we propose PoseLLM, the first Large Language Model (LLM)-based pose estimation framework that replaces the linear projector with a nonlinear MLP vision-language connector. This lightweight two-layer MLP with GELU activation enables hierarchical cross-modal feature transformation, enhancing the fusion of visual patches and textual keypoint descriptions. Trained exclusively on COCO data, PoseLLM achieves 77.8 AP on the COCO validation set, outperforming LocLLM by +0.4 AP, while maintaining strong zero-shot generalization on Human-Art and MPII. Our work demonstrates that a simple yet powerful nonlinear connector significantly boosts localization accuracy without sacrificing generalization, advancing the state-of-the-art in language-guided pose estimation. Code is available at https://github.com/Ody-trek/PoseLLM.