ESARBench is the first unified benchmark for MLLM-driven UAV agents that must explore, locate clues, and decide on victim positions in photorealistic simulated SAR environments.
Refdrone: A challenging benchmark for referring expression comprehension in drone scenes
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
dataset 1
citation-polarity summary
years
2026 4polarities
background 3representative citing papers
Language-guided semantic cues from MLLM visual pipelines, steered by text embeddings, refine object semantics and boost grounding accuracy against occlusion and small objects.
UAV-Track VLA modifies the π0.5 VLA architecture with temporal compression and dual-branch decoding to reach 61.76% success and 269.65 average frames in long-distance pedestrian tracking on a new 890K-frame UAV dataset, while cutting inference latency by 33.4%.
This survey organizes aerial vision-language navigation methods into five architectural categories, critically reviews evaluation infrastructure, and synthesizes seven open problems for LLM/VLM integration.
citing papers explorer
-
ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue
ESARBench is the first unified benchmark for MLLM-driven UAV agents that must explore, locate clues, and decide on victim positions in photorealistic simulated SAR environments.
-
Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues
Language-guided semantic cues from MLLM visual pipelines, steered by text embeddings, refine object semantics and boost grounding accuracy against occlusion and small objects.
-
UAV-Track VLA: Embodied Aerial Tracking via Vision-Language-Action Models
UAV-Track VLA modifies the π0.5 VLA architecture with temporal compression and dual-branch decoding to reach 61.76% success and 269.65 average frames in long-distance pedestrian tracking on a new 890K-frame UAV dataset, while cutting inference latency by 33.4%.
-
Vision-Language Navigation for Aerial Robots: Towards the Era of Large Language Models
This survey organizes aerial vision-language navigation methods into five architectural categories, critically reviews evaluation infrastructure, and synthesizes seven open problems for LLM/VLM integration.