Related papers: SkyNative: A Native Multimodal Framework for Remot…

When applied to Image-to-text models, interpretability methods often provide token-by-token explanations namely, they compute a visual explanation for each token of the generated sequence. Those explanations are expensive to compute and…

Vision-language models (VLMs) have advanced rapidly, but their ability to capture spatial relationships remains a blindspot. Current VLMs are typically built with contrastive language-image pretraining (CLIP) style image encoders. The…

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving their spatial intelligence remains a challenge. Existing 3D MLLMs always rely on additional 3D or…

The rapid advancement of generative models has intensified the challenge of detecting and interpreting visual forgeries, necessitating robust frameworks for image forgery detection while providing reasoning as well as localization. While…

The mainstream paradigm of remote sensing image interpretation has long been dominated by vision-centered models, which rely on visual features for semantic understanding. However, these models face inherent limitations in handling…

We propose SatelliteFormula, a novel symbolic regression framework that derives physically interpretable expressions directly from multi-spectral remote sensing imagery. Unlike traditional empirical indices or black-box learning models,…

The interpretation of multi-temporal remote sensing imagery is critical for monitoring Earth's dynamic processes-yet previous change detection methods, which produce binary or semantic masks, fall short of providing human-readable insights…

Multimodal Small-to-Medium sized Language Models (MSLMs) have demonstrated strong capabilities in integrating visual and textual information but still face significant limitations in visual comprehension and mathematical reasoning,…

Current Large Multimodal Models (LMMs) in Earth Observation typically neglect the critical "vertical" dimension, limiting their reasoning capabilities in complex remote sensing geometries and disaster scenarios where physical spatial…

Building on recent advances in language-based reasoning models, we explore multimodal reasoning that integrates vision and text. Existing multimodal benchmarks primarily test visual extraction combined with text-based reasoning, lacking…

Multimodal Large Language Models (MLLMs) have made remarkable progress on vision-language reasoning, yet most methods still compress visual evidence into discrete textual thoughts, creating an information bottleneck for fine-grained…

Vision-language models (VLMs) excel at multimodal understanding, yet their text-only decoding forces them to verbalize visual reasoning, limiting performance on tasks that demand visual imagination. Recent attempts train VLMs to render…

VQ-based image generation typically follows a two-stage pipeline: a tokenizer encodes images into discrete tokens, and a generative model learns their dependencies for reconstruction. However, improved tokenization in the first stage does…

Video-based spatial reasoning -- such as estimating distances, judging directions, or understanding layouts from multiple views -- requires selecting informative frames and, when needed, actively seeking additional viewpoints during…

Autonomous robotic systems require spatio-temporal understanding of dynamic environments to ensure reliable navigation and interaction. While Vision-Language Models (VLMs) provide open-world semantic priors, they lack grounding in 3D…

Multimodal latent reasoning has emerged as a promising paradigm that replaces explicit Chain-of-Thought (CoT) decoding with implicit feature propagation, simultaneously enhancing representation informativeness and reducing inference…

Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either…

Recent advances in prompt learning have allowed users to interact with artificial intelligence (AI) tools in multi-turn dialogue, enabling an interactive understanding of images. However, it is difficult and inefficient to deliver…

We explore the power of spatial context as a self-supervisory signal for learning visual representations. In particular, we propose spatial context networks that learn to predict a representation of one image patch from another image patch,…

Contemporary Vision-Language Models (VLMs) achieve strong performance on a wide range of tasks by pairing a vision encoder with a pre-trained language model, fine-tuned for visual-text inputs. Yet despite these gains, it remains unclear how…