Related papers: Beyond GSD-as-Token: Continuous Scale Conditioning…

Spatial reasoning and visual grounding are core capabilities for vision-language models (VLMs), yet most medical VLMs produce predictions without transparent reasoning or spatial evidence. Existing benchmarks also evaluate VLMs on isolated…

Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing images based on free-form natural language expressions. Existing approaches are typically constrained to closed-set vocabularies, limiting their applicability…

Low-Rank Adaptation (LoRA) fine-tunes large models by learning low-rank updates on top of frozen weights, dramatically reducing trainable parameters and memory. In this work, we address the gap between training with full steps with low-rank…

While vision language models (VLMs) excel in 2D semantic visual understanding, their ability to quantitatively reason about 3D spatial relationships remains under-explored, due to the deficiency of 2D images' spatial representation ability.…

High-quality digital terrain models derived from airborne laser scanning (ALS) data are essential for a wide range of geospatial analyses, and their generation typically relies on robust ground filtering (GF) to separate point clouds across…

Cross-view geo-localization aims to estimate the location of a query ground image by matching it to a reference geo-tagged aerial images database. As an extremely challenging task, its difficulties root in the drastic view changes and…

As the demand for high-resolution image processing in Large Vision-Language Models (LVLMs) grows, sub-image partitioning has become a popular approach for mitigating visual information loss associated with fixed-resolution processing.…

Deploying vision-language models (VLMs) in clinical settings demands auditable behavior under realistic failure conditions, yet the failure landscape of frontier VLMs on specialized medical inputs is poorly characterized. We audit five…

Vision-language models (VLMs) often struggle with geometric reasoning due to their limited perception of fundamental diagram elements. To tackle this challenge, we introduce GeoPerceive, a benchmark comprising diagram instances paired with…

Foundation models trained via vision-language pretraining have demonstrated strong zero-shot capabilities across diverse image domains, yet their application to volumetric medical imaging remains limited. We introduce MedCT-VLM: Medical CT…

In the field of Class Incremental Object Detection (CIOD), creating models that can continuously learn like humans is a major challenge. Pseudo-labeling methods, although initially powerful, struggle with multi-scenario incremental learning…

Recent advances in large multimodal models (LMMs) have recognized fine-grained grounding as an imperative factor of visual understanding and dialogue. However, the benefits of such representation in LMMs are limited to the natural image…

As deep learning technology continues to advance, image generation models, especially models like Stable Diffusion, are finding increasingly widespread application in visual arts creation. However, these models often face challenges such as…

The Segment Anything Model (SAM) stands as a foundational framework for image segmentation. While it exhibits remarkable zero-shot generalization in typical scenarios, its advantage diminishes when applied to specialized domains like…

Supervised machine learning methods for geological mapping via remote sensing face limitations due to the scarcity of accurately labelled training data that can be addressed by unsupervised learning, such as dimensionality reduction and…

Vision-language models encode continuous geometry that their text pathway fails to express: a 6,000-parameter linear probe extracts hand joint angles at 6.1 degrees MAE from frozen features, while the best text output achieves only 20.0…

Vision Language Models (VLMs) have recently achieved significant progress in bridging visual perception and linguistic reasoning. Recently, OpenAI o3 model introduced a zoom-in search strategy that effectively elicits active perception…

Vision-language models (VLMs) have demonstrated strong cross-modal capabilities, yet most work remains limited to 2D data and assumes binary supervision (i.e., positive vs. negative pairs), overlooking the continuous and structured…

Remote sensing visual grounding (RSVG) aims to localize specific targets in remote sensing images using natural language expressions. However, existing methods are restricted to single-sensor domains, i.e., either optical or synthetic…

Semi-supervised semantic segmentation (S4) has advanced remote sensing (RS) analysis by leveraging unlabeled data through pseudo-labeling and consistency learning. However, existing S4 studies often rely on small-scale datasets and models,…