Related papers: Traceable Evidence Enhanced Visual Grounded Reason…
Multimodal large language models (MLLMs) have shown promising reasoning abilities, yet evaluating their performance in specialized domains remains challenging. STEM reasoning is a particularly valuable testbed because it provides highly…
Assessing progress toward the Sustainable Development Goals (SDGs) requires multi-step reasoning over visual cues, contextual knowledge, and development indicators, where incomplete evidence use and imperfect evidence integration can…
Recent text-to-image (T2I) models have demonstrated impressive capabilities in photorealistic synthesis and instruction following. However, their reliability in knowledge-intensive settings remains largely unexplored. Unlike natural image…
Large Language Models (LLMs) are increasingly excelling and outpacing human performance on many tasks. However, to improve LLM reasoning, researchers either rely on ad-hoc generated datasets or formal mathematical proof systems such as the…
Different from Object Detection, Visual Grounding deals with detecting a bounding box for each text-image pair. This one box for each text-image data provides sparse supervision signals. Although previous works achieve impressive results,…
We study fine-grained referring image segmentation via a decoupled reason-then-segment pipeline. A vision-language model (VLM) receives an image and a natural-language query, reasons about the scene, and emits structured spatial prompts: a…
The evaluation of text-generative vision-language models is a challenging yet crucial endeavor. By addressing the limitations of existing Visual Question Answering (VQA) benchmarks and proposing innovative evaluation methodologies, our…
Low-level visual perception underpins reliable remote sensing (RS) image analysis, yet current image quality assessment (IQA) methods output uninterpretable scalar scores rather than characterizing physics-driven RS degradations, deviating…
Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and complex image editing tasks that require implicit reasoning,…
The capability of large language models to handle long-context information is crucial across various real-world applications. Existing evaluation methods often rely either on real-world long texts, making it difficult to exclude the…
Visual grounding aims to localize the object referred to in an image based on a natural language query. Although progress has been made recently, accurately localizing target objects within multiple-instance distractions (multiple objects…
Adaptive multimodal reasoning has emerged as a promising frontier in Vision-Language Models (VLMs), aiming to dynamically modulate between tool-augmented visual reasoning and text reasoning to enhance both effectiveness and efficiency.…
Visual Grounding, also known as Referring Expression Comprehension and Phrase Grounding, aims to ground the specific region(s) within the image(s) based on the given expression text. This task simulates the common referential relationships…
Structured tables are essential for conveying high-density information in professional domains such as finance, healthcare, and scientific research. Despite the progress in Multimodal Large Language Models (MLLMs), reasoning performance…
Recently, Multimodal Large Language Models (MLLMs) have made rapid progress, particularly in enhancing their reasoning capabilities. However, existing reasoning benchmarks still primarily assess language-based reasoning, often treating…
In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or science domains. This…
Recent progress in Vision Language Models (VLMs) has raised the question of whether they can reliably perform nonverbal reasoning. To this end, we introduce VRIQ (Visual Reasoning IQ), a novel benchmark designed to assess and analyze the…
Real-world robots localize objects from natural-language instructions while scenes around them keep changing. Yet most of the existing 3D visual grounding (3DVG) method still assumes a reconstructed and up-to-date point cloud, an assumption…
We introduce Generative Universal Verifier, a novel concept and plugin designed for next-generation multimodal reasoning in vision-language models and unified multimodal models, providing the fundamental capability of reflection and…
Collaborative reasoning for understanding image-question pairs is a very critical but underexplored topic in interpretable visual question answering systems. Although very recent studies have attempted to use explicit compositional…