arXiv:2610.31838v1 Announce Type: new Abstract: This paper introduces Sense-Aligned Grounding Evaluation (SAGE), a unified 10-candidate image-selection benchmark that reformulates VWSD, VerSe, and Wi...
WorldGenBench is a benchmark that tests text‑to‑image models on their ability to combine factual grounding with contextual reasoning. It introduces the Knowledge Checklist Score to evaluate whether generated images reflect both explicit and implicit semantic elements. The study finds that while some proprietary models perform well, most open‑source systems struggle, especially with culturally diverse and scientific content, revealing common failure modes such as semantic hallucination and underrepresentation of non‑Western knowledge.
arXiv:2608.30247v1 Announce Type: new Abstract: Recent unified open-vocabulary detection (OVD) supports heterogeneous prompts, including text queries, visual exemplars, and their combinations, but of...
GeoNLI introduces a unified, modular pipeline that combines advanced SAM variants with multimodal large language models to perform satellite image captioning, visual question answering (VQA), and visual grounding. The EarthMind model achieves strong results on captioning and VQA, while multiple RemoteSAM-SAM and DiffuSAM pipelines are used for grounding, ultimately employing a majority‑voting ensemble across several models. The system reports 82% captioning accuracy, 83.32% VQA accuracy, and 64.94% grounding accuracy, demonstrating improved consistency over task‑specific approaches.
arXiv:2607. 16727v1 Announce Type: new Abstract: Autoregressive multimodal large language models (MLLMs) suffer from error snowballing: a single incorrect inference early in a chainof-thought (CoT) trace corrupts all downstream reasoning.
arXiv:2608. 04726v1 Announce Type: new Abstract: Multimodal large language models increasingly reason over screenshots and documents where the task itself may be written in pixels.
UReason is a benchmark that evaluates how well unified multimodal models (UMMs) align textual reasoning with image generation. It contains 2,000 human‑curated instances across five reasoning‑intensive tasks—Code, Arithmetic, Spatial, Attribute, and Text—and compares direct generation, reasoning‑guided generation, and decontextualized generation. The study finds that while reasoning‑guided generation improves over direct generation, decontextualized generation consistently outperforms it, indicating that the visual semantics in textual reasoning are not reliably reflected in the generated images.
arXiv:2603. 14342v2 Announce Type: replace-cross Abstract: Modern agricultural data is sourced from diverse platforms and spans multiple spatial scales, ranging from ground-level close-up photography to Unmanned Aerial Vehicle (UAV) aerial observation and satellite remote sensing imagery.
PRISM-BENCH is a new benchmark comprising 1,000 expert‑curated vision‑language questions across five under‑represented reasoning categories, each paired with an idealized reasoning trace validated by a second annotator. It introduces diagnostics beyond final‑answer accuracy: a perception probe that attributes about 85% of frontier‑model failures to misperception, and trace alignment that predicts answer correctness with a macro AUROC of 0.66. The benchmark also presents CORE, an efficiency‑aware metric that reorders 24.2% of model pairs relative to accuracy while remaining uncorrelated with response length, revealing that recent gains are driven by recognition rather than spatial grounding.
The paper introduces TerraAgent, a training‑free framework that enhances remote sensing visual question answering by integrating three modules: GDR for demonstration retrieval, MACE for evidence‑typed sub‑question decomposition, and CVA for counterfactual evidence auditing. It demonstrates significant improvements on multiple benchmarks, raising accuracy, visual‑dependency scores, and reducing prior‑only answers and hallucinations without fine‑tuning.
PANORAMA introduces a new panoptic grounded captioning framework that jointly generates detailed image captions and associates each phrase with precise pixel-level masks. The authors create PanoCaps, a human‑annotated benchmark with dense captions and near‑complete pixel coverage, and propose a phrase‑mask matching protocol with a generalized Panoptic Quality metric. PANORAMA conditions a pretrained segmenter on contextualized phrase representations, learns to select appropriate masks, and achieves state‑of‑the‑art grounding performance on PanoCaps and other pixel‑level tasks.
Cross-image comparative reasoning remains challenging for vision-language models (VLMs), especially when correct prediction requires fine-grained attribute grounding and globally consistent reasoning. We present CoRe, a unified framework for this problem.