Survey of Multimodal Geospatial Foundation Models: Techniques, Applications, and Challenges

Foundation models have transformed natural language processing and computer vision, and their impact is now reshaping remote sensing image analysis. With powerful generalization and transfer learning capabilities, they align naturally with the multimodal, multi-resolution, and multi-temporal characteristics of remote sensing data. To address unique challenges in the field, multimodal geospatial foundation models (GFMs) have emerged as a dedicated research frontier. This survey delivers a comprehensive review of multimodal GFMs from a modality-driven perspective, covering five core visual and vision-language modalities. We examine how differences in imaging physics and data representation shape interaction design, and we analyze key techniques for alignment, integration, and knowledge transfer to tackle modality heterogeneity, distribution shifts, and semantic gaps. Advances in training paradigms, architectures, and task-specific adaptation strategies are systematically assessed alongside a wealth of emerging benchmarks. Representative multimodal visual and vision-language GFMs are evaluated across ten downstream tasks, with insights into their architectures, performance, and application scenarios. Real-world case studies, spanning land cover mapping, agricultural monitoring, disaster response, climate studies, and geospatial intelligence, demonstrate the practical potential of GFMs. Finally, we outline pressing challenges in domain generalization, interpretability, efficiency, and privacy, and chart promising avenues for future research.

Robust Atypical Mitosis Classification with DenseNet121: Stain-Aware Augmentation and Hybrid Loss for Domain Generalization

Atypical mitotic figures are important biomarkers of tumor aggressiveness in histopathology, yet reliable recognition remains challenging due to severe class imbalance and variability across imaging domains. We present a DenseNet-121-based framework tailored for atypical mitosis classification in the MIDOG 2025 (Track 2) setting. Our method integrates stain-aware augmentation (Macenko), geometric and intensity transformations, and imbalance-aware learning via weighted sampling with a hybrid objective combining class-weighted binary cross-entropy and focal loss. Trained end-to-end with AdamW and evaluated across multiple independent domains, the model demonstrates strong generalization under scanner and staining shifts, achieving balanced accuracy 85.0%, AUROC 0.927, sensitivity 89.2%, and specificity 80.9% on the official test set. These results indicate that combining DenseNet-121 with stain-aware augmentation and imbalance-adaptive objectives yields a robust, domain-generalizable framework for atypical mitosis classification suitable for real-world computational pathology workflows.

USF-MAE: Ultrasound Self-Supervised Foundation Model with Masked Autoencoding

Ultrasound imaging is one of the most widely used diagnostic modalities, offering real-time, radiation-free assessment across diverse clinical domains. However, interpretation of ultrasound images remains challenging due to high noise levels, operator dependence, and limited field of view, resulting in substantial inter-observer variability. Current Deep Learning approaches are hindered by the scarcity of large labeled datasets and the domain gap between general and sonographic images, which limits the transferability of models pretrained on non-medical data. To address these challenges, we introduce the Ultrasound Self-Supervised Foundation Model with Masked Autoencoding (USF-MAE), the first large-scale self-supervised MAE framework pretrained exclusively on ultrasound data. The model was pre-trained on 370,000 2D and 3D ultrasound images curated from 46 open-source datasets, collectively termed OpenUS-46, spanning over twenty anatomical regions. This curated dataset has been made publicly available to facilitate further research and reproducibility. Using a Vision Transformer encoder-decoder architecture, USF-MAE reconstructs masked image patches, enabling it to learn rich, modality-specific representations directly from unlabeled data. The pretrained encoder was fine-tuned on three public downstream classification benchmarks: BUS-BRA (breast cancer), MMOTU-2D (ovarian tumors), and GIST514-DB (gastrointestinal stromal tumors). Across all tasks, USF-MAE consistently outperformed conventional CNN and ViT baselines, achieving F1-scores of 81.6%, 79.6%, and 82.4%, respectively. Despite not using labels during pretraining, USF-MAE approached the performance of the supervised foundation model UltraSam on breast cancer classification and surpassed it on the other tasks, demonstrating strong cross-anatomical generalization.

Equivariant Neural Networks for General Linear Symmetries on Lie Algebras

Encoding symmetries is a powerful inductive bias for improving the generalization of deep neural networks. However, most existing equivariant models are limited to simple symmetries like rotations, failing to address the broader class of general linear transformations, GL(n), that appear in many scientific domains. We introduce Reductive Lie Neurons (ReLNs), a novel neural network architecture exactly equivariant to these general linear symmetries. ReLNs are designed to operate directly on a wide range of structured inputs, including general n-by-n matrices. ReLNs introduce a novel adjoint-invariant bilinear layer to achieve stable equivariance for both Lie-algebraic features and matrix-valued inputs, without requiring redesign for each subgroup. This architecture overcomes the limitations of prior equivariant networks that only apply to compact groups or simple vector data. We validate ReLNs' versatility across a spectrum of tasks: they outperform existing methods on algebraic benchmarks with sl(3) and sp(4) symmetries and achieve competitive results on a Lorentz-equivariant particle physics task. In 3D drone state estimation with geometric uncertainty, ReLNs jointly process velocities and covariances, yielding significant improvements in trajectory accuracy. ReLNs provide a practical and general framework for learning with broad linear group symmetries on Lie algebras and matrix-valued data. Project page: https://reductive-lie-neuron.github.io/

Frustratingly Easy Task-aware Pruning for Large Language Models

Pruning provides a practical solution to reduce the resources required to run large language models (LLMs) to benefit from their effective capabilities as well as control their cost for training and inference. Research on LLM pruning often ranks the importance of LLM parameters using their magnitudes and calibration-data activations and removes (or masks) the less important ones, accordingly reducing LLMs' size. However, these approaches primarily focus on preserving the LLM's ability to generate fluent sentences, while neglecting performance on specific domains and tasks. In this paper, we propose a simple yet effective pruning approach for LLMs that preserves task-specific capabilities while shrinking their parameter space. We first analyze how conventional pruning minimizes loss perturbation under general-domain calibration and extend this formulation by incorporating task-specific feature distributions into the importance computation of existing pruning algorithms. Thus, our framework computes separate importance scores using both general and task-specific calibration data, partitions parameters into shared and exclusive groups based on activation-norm differences, and then fuses their scores to guide the pruning process. This design enables our method to integrate seamlessly with various foundation pruning techniques and preserve the LLM's specialized abilities under compression. Experiments on widely used benchmarks demonstrate that our approach is effective and consistently outperforms the baselines with identical pruning ratios and different settings.

PSScreen V2: Partially Supervised Multiple Retinal Disease Screening

In this work, we propose PSScreen V2, a partially supervised self-training framework for multiple retinal disease screening. Unlike previous methods that rely on fully labelled or single-domain datasets, PSScreen V2 is designed to learn from multiple partially labelled datasets with different distributions, addressing both label absence and domain shift challenges. To this end, PSScreen V2 adopts a three-branch architecture with one teacher and two student networks. The teacher branch generates pseudo labels from weakly augmented images to address missing labels, while the two student branches introduce novel feature augmentation strategies: Low-Frequency Dropout (LF-Dropout), which enhances domain robustness by randomly discarding domain-related low-frequency components, and Low-Frequency Uncertainty (LF-Uncert), which estimates uncertain domain variability via adversarially learned Gaussian perturbations of low-frequency statistics. Extensive experiments on multiple in-domain and out-of-domain fundus datasets demonstrate that PSScreen V2 achieves state-of-the-art performance and superior domain generalization ability. Furthermore, compatibility tests with diverse backbones, including the vision foundation model DINOv2, as well as evaluations on chest X-ray datasets, highlight the universality and adaptability of the proposed framework. The codes are available at https://github.com/boyiZheng99/PSScreen_V2.

DeepSalt: Bridging Laboratory and Satellite Spectra through Domain Adaptation and Knowledge Distillation for Large-Scale Soil Salinity Estimation

Soil salinization poses a significant threat to both ecosystems and agriculture because it limits plants' ability to absorb water and, in doing so, reduces crop productivity. This phenomenon alters the soil's spectral properties, creating a measurable relationship between salinity and light reflectance that enables remote monitoring. While laboratory spectroscopy provides precise measurements, its reliance on in-situ sampling limits scalability to regional or global levels. Conversely, hyperspectral satellite imagery enables wide-area observation but lacks the fine-grained interpretability of laboratory instruments. To bridge this gap, we introduce DeepSalt, a deep-learning-based spectral transfer framework that leverages knowledge distillation and a novel Spectral Adaptation Unit to transfer high-resolution spectral insights from laboratory-based spectroscopy to satellite-based hyperspectral sensing. Our approach eliminates the need for extensive ground sampling while enabling accurate, large-scale salinity estimation, as demonstrated through comprehensive empirical benchmarks. DeepSalt achieves significant performance gains over methods without explicit domain adaptation, underscoring the impact of the proposed Spectral Adaptation Unit and the knowledge distillation strategy. The model also effectively generalized to unseen geographic regions, explaining a substantial portion of the salinity variance.

MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs

The widespread adoption of Large Language Models (LLMs) raises critical concerns about the factual accuracy of their outputs, especially in high-risk domains such as biomedicine, law, and education. Existing evaluation methods for short texts often fail on long-form content due to complex reasoning chains, intertwined perspectives, and cumulative information. To address this, we propose a systematic approach integrating large-scale long-form datasets, multi-agent verification mechanisms, and weighted evaluation metrics. We construct LongHalluQA, a Chinese long-form factuality dataset; and develop MAD-Fact, a debate-based multi-agent verification system. We introduce a fact importance hierarchy to capture the varying significance of claims in long-form texts. Experiments on two benchmarks show that larger LLMs generally maintain higher factual consistency, while domestic models excel on Chinese content. Our work provides a structured framework for evaluating and enhancing factual reliability in long-form LLM outputs, guiding their safe deployment in sensitive domains.

On Generalization in Agentic Tool Calling: CoreThink Agentic Reasoner and MAVEN Dataset

Generalization across Agentic tool-calling environments remains a key unsolved challenge in developing reliable agentic reasoning systems. While large language models (LLMs) demonstrate strong performance on isolated benchmarks, their ability to transfer reasoning strategies and co-ordinate tools across diverse domains is poorly understood. In this work, we conduct a large-scale evaluation of state-of-the-art LLMs on multiple tool-calling benchmarksBFCL v3, TauBench, Tau2Bench, and AceBenchand introduce MAVEN (Math & Physics Adversarial Verification & Evaluation Network), a new out of distribution (OOD) benchmark designed to stress-test multi-step reasoning through explicit verification and adversarial task composition. Our results show that most current models achieve below 50% accuracy on MAVEN, revealing a significant generalization gap across tool-use settings. To address this, we present the CoreThink Agentic Reasoner, a framework that augments LLMs with a lightweight symbolic reasoning layer for structured decomposition and adaptive tool orchestration. Without additional training, it generalizes across all benchmarks, achieving state-of-the-art performance with 530% improvements over existing baselines at roughly one-tenth the computational cost.

RL-AUX: Reinforcement Learning for Auxiliary Task Generation

Auxiliary Learning (AL) is a special case of Multi-task Learning (MTL) in which a network trains on auxiliary tasks to improve performance on its main task. This technique is used to improve generalization and, ultimately, performance on the network's main task. AL has been demonstrated to improve performance across multiple domains, including navigation, image classification, and natural language processing. One weakness of AL is the need for labeled auxiliary tasks, which can require human effort and domain expertise to generate. Meta Learning techniques have been used to solve this issue by learning an additional auxiliary task generation network that can create helpful tasks for the primary network. The most prominent techniques rely on Bi-Level Optimization, which incurs computational cost and increased code complexity. To avoid the need for Bi-Level Optimization, we present an RL-based approach to dynamically create auxiliary tasks. In this framework, an RL agent is tasked with selecting auxiliary labels for every data point in a training set. The agent is rewarded when their selection improves the performance on the primary task. We also experiment with learning optimal strategies for weighing the auxiliary loss per data point. On the 20-Superclass CIFAR100 problem, our RL approach outperforms human-labeled auxiliary tasks and performs as well as a prominent Bi-Level Optimization technique. Our weight learning approaches significantly outperform all of these benchmarks. For example, a Weight-Aware RL-based approach helps the VGG16 architecture achieve 80.9% test accuracy while the human-labeled auxiliary task setup achieved 75.53%. The goal of this work is to (1) prove that RL is a viable approach to dynamically generate auxiliary tasks and (2) demonstrate that per-sample auxiliary task weights can be learned alongside the auxiliary task labels and can achieve strong results.