SkyVLaM: Multimodal Large Language Model for UAV Video Understanding in Remote Sensing
On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
Abstract (arXiv)
Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved remote sensing (RS) multimodal understanding. Language-conditioned segmentation is crucial for fine-grained target understanding in Unmanned Aerial Vehicle (UAV) videos. However, this task remains challenging due to the prevalence of small, visually ambiguous targets and dynamic aerial perspectives. In this paper, we propose SkyVLaM, a multimodal large language model for UAV video understanding. SkyVLaM constructs sparse tokens directly from patch-level video representations through a temporal basis perceiver, regularizes the sparse basis to encourage complementary temporal cues, and adaptively selects a temporally coherent dense segment for high-resolution inspection. The resulting sparse and dense tokens are jointly processed by a large language model for query-conditioned segmentation. We further build SkyVid, consisting of SkyVid-VGCG and SkyVid-RVOS for video grounded conversation generation and referring video object segmentation, respectively. SkyVid contains 101 videos, 33.6K frames, and 1.53M pixel-level object instances. Experiments show that SkyVLaM provides a more effective allocation of the visual token budget and improves language-conditioned video segmentation in UAV scenarios.
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 13 of its 51 references that are in the map. First posted on arXiv 19 Jul 2026.
Builds on
13 of 51 references.
Closest ancestors · 4
Same direction, newest first
- 2025GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution27 May
- 2025GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing16 Mar
- 2024RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts7 Dec
- 2024SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding14 Jun
Other references · 9
- 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
- 2025Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videoscited by 159
- 2024SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Modelscited by 125
- 2024Frame-Voyager: Learning to Query Frames for Video Large Language Modelscited by 83
- 2024TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Datacited by 70
- 2025StreamingTOM: Streaming Token Compression for Efficient Video Understandingcited by 43
- 2025Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoningcited by 37
- 2025FOCUS: Efficient Keyframe Selection for Long Video Understandingcited by 37
- 2026TiFRe: Text-guided Video Frame Reduction for Efficient Video Multi-modal Large Language Modelscited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Memory-Augmented Multimodal Large Language Models for Small Object Understanding in Streaming Aerial Videos
- 2026Can Vision-Language Models Think from the Sky? Unifying UAV Reasoning and Generation
- 2026PixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation
- 2026AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning
- 2026ReVA: A Scene-Centric Dataset Beyond Repetition for Remote Sensing Video Question Answering
- 2026DVGBench: Implicit-to-Explicit Visual Grounding Benchmark in UAV Imagery with Large Vision-Language Models
- 2026AirNav: A Large-Scale UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructions
- 2026UAVBench and UAVIT-1M: Benchmarking and Enhancing MLLMs for Low-Altitude UAV Vision-Language Understanding