Related papers: MoCoLSK: Modality Conditioned High-Resolution Down…
In this work, we present Multi-Level Contrastive Learning for Dense Prediction Task (MCL), an efficient self-supervised method for learning region-level feature representation for dense prediction tasks. Our method is motivated by the three…
Geospatial Copilots unlock unprecedented potential for performing Earth Observation (EO) applications through natural language instructions. However, existing agents rely on overly simplified single tasks and template-based prompts,…
Geospatial Copilots hold immense potential for automating Earth observation (EO) and climate monitoring workflows, yet their reliance on large-scale models such as GPT-4o introduces a paradox: tools intended for sustainability studies often…
Collaborative learning enhances the performance and adaptability of multi-robot systems in complex tasks but faces significant challenges due to high communication overhead and data heterogeneity inherent in multi-robot tasks. To this end,…
Relative Geologic Time (RGT) estimation from seismic data is a cornerstone of subsurface structural modeling, depositional evolution analysis, and reservoir characterization, supporting horizon correlation and depositional system…
Recent years have witnessed the fast growth in telecommunication (Telco) techniques from 2G to upcoming 5G. Precise outdoor localization is important for Telco operators to manage, operate and optimize Telco networks. Differing from GPS,…
Hi-resolution spectroscopy (R > 25,000) has recently emerged as one of the leading methods to detect atomic and molecular species in the atmospheres of exoplanets. However, it has so far been lacking in a robust method to extract…
Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge stems from two key…
Vision-Language Models (VLMs) in remote sensing often fail at complex analytical tasks, a limitation stemming from their end-to-end training paradigm that bypasses crucial reasoning steps and leads to unverifiable outputs. To address this…
Document visual question answering requires models not only to answer questions correctly, but also to precisely localize answers within complex document layouts. While large vision-language models (VLMs) achieve strong spatial grounding,…
Modern challenges arising in the fields of theoretical and experimental physics require new powerful tools for high-precision electronic structure modelling; one of the most perspective tools is the relativistic Fock space coupled cluster…
The reconstruction of ocean subsurface temperature (OST) using satellite remote sensing data holds significant scientific value for advancing the understanding of ocean dynamics and climate variability. However, the scarcity of subsurface…
Remote sensing image interpretation plays a critical role in environmental monitoring, urban planning, and disaster assessment. However, acquiring high-quality labeled data is often costly and time-consuming. To address this challenge, we…
The environmental impact of Large Language Models (LLMs) on data centers hosting these models is becoming a significant concern. While many efforts have focused on reducing the substantial training overhead of LLMs, carbon and water…
Spatio-Temporal prediction plays a critical role in smart city construction. Jointly modeling multiple spatio-temporal tasks can further promote an intelligent city life by integrating their inseparable relationship. However, existing…
During few last years, climate change including global warming which is attributed to human activities and also its long-term adverse effects on the planet's functions have been identified as the most challenging discussion topics which…
Large language models represent a groundbreaking shift in generative AI. Yet, these advances come with a significant challenge: the high cost of model serving. To mitigate these costs, consumer-grade GPUs emerge as a more affordable…
As large language models (LLMs) are applied to increasingly longer and more complex tasks, there is a growing need for realistic long-context benchmarks that require selective reading and integration of heterogeneous, multi-modal…
The surge in rich multimodal content on social media platforms has greatly advanced Multimodal Sentiment Analysis (MSA), with Large Language Models (LLMs) further accelerating progress in this field. Current approaches primarily leverage…
The recently proposed sparsifying transform models incur low computational cost and have been applied to medical imaging. Meanwhile, deep models with nested network structure reveal great potential for learning features in different layers.…