SenseBench is the first physics-based benchmark with 10K+ instances and dual protocols to evaluate VLMs on remote sensing low-level perception and diagnostic description, revealing domain bias and specific failure modes.
Rsunivlm: A unified vision language model for remote sensing via granularity-oriented mixture of experts
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
baseline 2
citation-polarity summary
fields
cs.CV 6years
2026 6verdicts
UNVERDICTED 6representative citing papers
DualComp uses a lightweight router to split visual token compression into a semantic stream with size-adaptive clustering and a geometric stream with path-tracing recovery, enabling low-cost high-fidelity UHR remote sensing interpretation.
RemoteAgent uses RL fine-tuning on VagueEO to align MLLMs for vague EO intent recognition, handling simple tasks internally and routing dense predictions to tools via Model Context Protocol.
RemoteZero replaces coordinate supervision with intrinsic semantic verification to enable box-free GRPO training and self-evolution for geospatial reasoning.
RemoteShield improves robustness of Earth observation MLLMs by training on semantic equivalence clusters of clean and perturbed inputs via preference learning to maintain consistent reasoning under noise.
Delta-LLaVA adds Change-Enhanced Attention, Change-SEG with prior embeddings, and Local Causal Attention to MLLMs to overcome temporal blindness, outperforming general models on a new unified benchmark for bi- and tri-temporal remote sensing tasks.
citing papers explorer
-
SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models
SenseBench is the first physics-based benchmark with 10K+ instances and dual protocols to evaluate VLMs on remote sensing low-level perception and diagnostic description, revealing domain bias and specific failure modes.
-
Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding
DualComp uses a lightweight router to split visual token compression into a semantic stream with size-adaptive clustering and a geometric stream with path-tracing recovery, enabling low-cost high-fidelity UHR remote sensing interpretation.
-
RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs
RemoteAgent uses RL fine-tuning on VagueEO to align MLLMs for vague EO intent recognition, handling simple tasks internally and routing dense predictions to tools via Model Context Protocol.
-
RemoteZero: Geospatial Reasoning with Zero Human Annotations
RemoteZero replaces coordinate supervision with intrinsic semantic verification to enable box-free GRPO training and self-evolution for geospatial reasoning.
-
RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observation
RemoteShield improves robustness of Earth observation MLLMs by training on semantic equivalence clusters of clean and perturbed inputs via preference learning to maintain consistent reasoning under noise.
-
Decoding the Delta: Unifying Remote Sensing Change Detection and Understanding with Multimodal Large Language Models
Delta-LLaVA adds Change-Enhanced Attention, Change-SEG with prior embeddings, and Local Causal Attention to MLLMs to overcome temporal blindness, outperforming general models on a new unified benchmark for bi- and tri-temporal remote sensing tasks.