Related papers: EVE: A Domain-Specific LLM Framework for Earth Int…

Are current Vision Language Models (VLMs) ready to comprehend and reason about complex embodied interactions in 3D environments? We introduce Embodied3DBench, a robot-centric benchmark targeting low-level spatial intelligence in embodied 3D…

Monitoring vegetation dynamics is crucial for addressing global environmental challenges like degradation and deforestation, but traditional remote sensing methods are often complex and resource-intensive. To overcome these barriers, we…

This work presents the network architecture EVP (Enhanced Visual Perception). EVP builds on the previous work VPD which paved the way to use the Stable Diffusion network for computer vision tasks. We propose two major enhancements. First,…

Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are…

In high-stakes domains, small task-specific vision models are crucial due to their low computational requirements and the availability of numerous methods to explain their results. However, these explanations often reveal that the models do…

Geospatial modeling provides critical solutions for pressing global challenges such as sustainability and climate change. Existing large language model (LLM)-based algorithm discovery frameworks, such as AlphaEvolve, excel at evolving…

Precise spatial reasoning is fundamental to robotic manipulation, yet the visual backbones of current vision-language-action (VLA) models are predominantly pretrained on 2D image data without explicit 3D geometric supervision, resulting in…

As the scale and complexity of spatiotemporal data continue to grow rapidly, the use of geospatial modeling on the Google Earth Engine (GEE) platform presents dual challenges: improving the coding efficiency of domain experts and enhancing…

Recent advances in Visual Language Models (VLMs) have demonstrated exceptional performance in visual reasoning tasks. However, geo-localization presents unique challenges, requiring the extraction of multigranular visual cues from images…

In the era of Large Language Models (LLMs), the Mixture of Experts (MoE) architecture has emerged as an effective approach for training extremely large models with improved computational efficiency. This success builds upon extensive prior…

World models - generative models that simulate environment dynamics conditioned on past observations and actions - are gaining prominence in planning, simulation, and embodied AI. However, evaluating their rollouts remains a fundamental…

Adapting Large Language Models (LLMs) to high-stakes vertical domains like insurance presents a significant challenge: scenarios demand strict adherence to complex regulations and business logic with zero tolerance for hallucinations.…

Recent advances in Earth Observation have focused on large-scale foundation models. However, these models are computationally expensive, limiting their accessibility and reuse for downstream tasks. In this work, we investigate compact…

Existing datasets for attribute value extraction (AVE) predominantly focus on explicit attribute values while neglecting the implicit ones, lack product images, are often not publicly available, and lack an in-depth human inspection across…

Large Language Models (LLMs) often produce hallucinations in retrieval-augmented or long-context generation, even when relevant evidence is present. This stems from two issues: head importance is treated as input-agnostic, and raw attention…

In recent years, Deep-Learning Earth System Models (DL-ESMs) have emerged as promising, computationally efficient complements to traditional Earth system models. Here, we present an evaluation framework for testing DL-ESMs from a…

We propose OutboundEval, a comprehensive benchmark for evaluating large language models (LLMs) in expert-level intelligent outbound calling scenarios. Unlike existing methods that suffer from three key limitations - insufficient dataset…

We have witnessed promising progress led by large language models (LLMs) and further vision language models (VLMs) in handling various queries as a general-purpose assistant. VLMs, as a bridge to connect the visual world and language…

Embedding is a useful technique to project a high-dimensional feature into a low-dimensional space, and it has many successful applications including link prediction, node classification and natural language processing. Current approaches…

Geospatial code generation is becoming a key frontier in integrating artificial intelligence with geo-scientific analysis, yet standardised automated evaluation tools for this task remain absent. This study presents AutoGEEval++, an…