Unfine-tuned MLLMs outperform fine-tuned models on remote sensing image captioning when captions are scored by their ability to reconstruct the source image, and a training-free self-correction method achieves SOTA performance.
Geopixel: Pixel grounding large multimodal model in remote sensing
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
GeoMeld provides a large-scale aligned multimodal remote sensing dataset with verified semantic captions and a joint pretraining method that improves downstream transfer and cross-sensor robustness in foundation models.
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.
MMLandmarks supplies 197k aerial and 329k ground images plus text and GPS for 18,557 landmarks to benchmark multimodal geo-spatial understanding.
InduceKV is a retrieval-based continual adaptation method that uses bilevel selection to build a compact set of inducing KV memories for fixed-footprint updates to multimodal LLMs.
GeoSearcher introduces anchor-centric reasoning supervised fine-tuning and process-faithful group relative policy optimization to improve MLLM-based remote sensing visual grounding.
Introduces MTRS task, MTRefSeg-21K benchmark of 21K image-text-mask triplets, and MTRefSeg-R1 LVLM baseline that outperforms standard models via two-stage change-aware training.
WOW-Seg proposes a word-free open-world segmentation model using Mask2Token and Cascade Attention Mask modules, reporting 89.7 semantic similarity and 82.4 semantic IoU on LVIS with one-eighth the parameters of prior SOTA plus a new 7,662-class benchmark.
The paper defines UAV reasoning segmentation, releases DRSeg—10,000 aerial images with reasoning QA and masks—and shows its PixDLM baseline beats prior reasoning-segmentation models under fine-tuning.
ProtoFlow models class prototypes as low-curvature trajectories with an explicit temporal vector field, reducing forgetting in class- and domain-incremental remote sensing segmentation by about 1.5–2.0 mIoU points.
B-GRTO pre-trains a segmentation tool via bootstrapped group relative optimization on GRPO rollouts, yielding substantial gains over plain GRPO on referring segmentation benchmarks.
citing papers explorer
-
Evaluating Remote Sensing Image Captions Beyond Metric Biases
Unfine-tuned MLLMs outperform fine-tuned models on remote sensing image captioning when captions are scored by their ability to reconstruct the source image, and a training-free self-correction method achieves SOTA performance.
-
GeoMeld: Toward Semantically Grounded Foundation Models for Remote Sensing
GeoMeld provides a large-scale aligned multimodal remote sensing dataset with verified semantic captions and a joint pretraining method that improves downstream transfer and cross-sensor robustness in foundation models.
-
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.
-
MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understanding
MMLandmarks supplies 197k aerial and 329k ground images plus text and GPS for 18,557 landmarks to benchmark multimodal geo-spatial understanding.
-
InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories
InduceKV is a retrieval-based continual adaptation method that uses bilevel selection to build a compact set of inducing KV memories for fixed-footprint updates to multimodal LLMs.
-
GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision
GeoSearcher introduces anchor-centric reasoning supervised fine-tuning and process-faithful group relative policy optimization to improve MLLM-based remote sensing visual grounding.
-
An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation
Introduces MTRS task, MTRefSeg-21K benchmark of 21K image-text-mask triplets, and MTRefSeg-R1 LVLM baseline that outperforms standard models via two-stage change-aware training.
-
WOW-Seg: A Word-free Open World Segmentation Model
WOW-Seg proposes a word-free open-world segmentation model using Mask2Token and Cascade Attention Mask modules, reporting 89.7 semantic similarity and 82.4 semantic IoU on LVIS with one-eighth the parameters of prior SOTA plus a new 7,662-class benchmark.
-
PixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation
The paper defines UAV reasoning segmentation, releases DRSeg—10,000 aerial images with reasoning QA and masks—and shows its PixDLM baseline beats prior reasoning-segmentation models under fine-tuning.
-
ProtoFlow: Mitigating Forgetting in Class-Incremental Remote Sensing Segmentation via Low-Curvature Prototype Flow
ProtoFlow models class prototypes as low-curvature trajectories with an explicit temporal vector field, reducing forgetting in class- and domain-incremental remote sensing segmentation by about 1.5–2.0 mIoU points.
-
B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation
B-GRTO pre-trains a segmentation tool via bootstrapped group relative optimization on GRPO rollouts, yielding substantial gains over plain GRPO on referring segmentation benchmarks.