PixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation
On the map: LLM reasoning → Spatial and embodied reasoning
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.
Key facts. Cited by 3 papers in the map (data through 7 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.
Builds on
6 of 63 references.
Closest ancestors · 1
Same direction, newest first
Other references · 5
- 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 891
- 2023GSVA: Generalized Segmentation via Multimodal Large Language Modelscited by 153
- 2024Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Modelscited by 112
- 2023InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Languagecited by 96
- 2025RIS-LAD: A Benchmark and Model for Referring Low-Altitude Drone Image Segmentationcited by 1
Built on by
Citing papers per year: 2026: 3.
3 papers.
- 2026Training-Free Open-Vocabulary Visual Grounding for Remote Sensing Images and Videoscited by 0
- 2026FIRM: Fine-Grained Intra-Token Representation of Masks for Remote Sensing Reasoning Segmentationcited by 0
- 2026FRESHLATENT: Channel-Aware Latent Adaptation for Resource-Constrained Embodied VLM Perceptioncited by 0
- 2026FRESHLATENT: Channel-Aware Latent Adaptation for Resource-Constrained Embodied VLM Perception24 Sep 2026
- 2026FIRM: Fine-Grained Intra-Token Representation of Masks for Remote Sensing Reasoning Segmentation14 Aug 2026
- 2026Training-Free Open-Vocabulary Visual Grounding for Remote Sensing Images and Videos15 Jun 2026
Similar, not cited
Close in wording, no citation either way
- 2026Can Vision-Language Models Think from the Sky? Unifying UAV Reasoning and Generation
- 2026Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System
- 2026Knowing the Self, Understanding the World: A Dual-Cognition Benchmark for UAV Spatio-temporal Reasoning with MLLMs
- 2026SkyVLaM: Multimodal Large Language Model for UAV Video Understanding in Remote Sensing
- 2025Multimodal Mathematical Reasoning Embedded in Aerial Vehicle Imagery: Benchmarking, Analysis, and Exploration
- 2026AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning
- 2025AeroReformer: Aerial Referring Transformer for UAV-based Referring Image Segmentation
- 2025UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning