# PixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation

arXiv: https://arxiv.org/abs/2604.15670 · HTML: https://mlsanity.com/paper/2604.15670/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 6 of its 63 references that are in the map.
- First posted on arXiv 17 Apr 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- 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, 6 of 6)

- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [GSVA: Generalized Segmentation via Multimodal Large Language Models](https://mlsanity.com/paper/2312.10103/) (2023)
- [Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models](https://mlsanity.com/paper/2403.03003/) (2024)
- [InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language](https://mlsanity.com/paper/2305.05662/) (2023)
- [RemoteReasoner: Towards Unifying Geospatial Reasoning Workflow](https://mlsanity.com/paper/2507.19280/) (2025)
- [RIS-LAD: A Benchmark and Model for Referring Low-Altitude Drone Image Segmentation](https://mlsanity.com/paper/2507.20920/) (2025)

## Built on by (most cited first, 3 of 3)

- [Training-Free Open-Vocabulary Visual Grounding for Remote Sensing Images and Videos](https://mlsanity.com/paper/2606.16124/) (2026)
- [FIRM: Fine-Grained Intra-Token Representation of Masks for Remote Sensing Reasoning Segmentation](https://mlsanity.com/paper/2608.13980/) (2026)
- [FRESHLATENT: Channel-Aware Latent Adaptation for Resource-Constrained Embodied VLM Perception](https://mlsanity.com/paper/2609.30629/) (2026)

## Abstract (arXiv)

Reasoning segmentation has recently expanded from ground-level scenes to remote-sensing imagery, yet UAV data poses distinct challenges, including oblique viewpoints, ultra-high resolutions, and extreme scale variations. To address these issues, we formally define the UAV Reasoning Segmentation task and organize its semantic requirements into three dimensions: Spatial, Attribute, and Scene-level reasoning. Based on this formulation, we construct DRSeg, a large-scale benchmark for UAV reasoning segmentation, containing 10k high-resolution aerial images paired with Chain-of-Thought QA supervision across all three reasoning types. As a benchmark companion, we introduce PixDLM, a simple yet effective pixel-level multimodal language model that serves as a unified baseline for this task. Experiments on DRSeg establish strong baseline results and highlight the unique challenges of UAV reasoning segmentation, providing a solid foundation for future research.