The paper introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that curre…

This paper introduces a new benchmark dataset and evaluation framework for 'data snapshot extraction,' focusing on identifying and localizing semantically meaningful analytical artifacts within operat…

The paper introduces DocFormBench, a new benchmark for content-aware document formatting, and proposes DocFormFlow, a workflow that improves formatting accuracy and efficiency by decoupling target loc…

This pilot study evaluates curator-guided multilingual art description using a small, on-premise VLM (Qwen2.5-VL-3B-Instruct) for German, Romanian, and Serbian, finding that language-specific adapters…

The paper introduces MLLM-Microscope, a system that analyzes the internal structure of multimodal large language models (MLLMs), finding that modality fusion significantly impacts the linearity and di…

The paper proposes a novel KAN-enhanced BiGRU architecture to improve legal document classification and summarization in a low-resource, multilingual setting using Bengali and English legal texts.

The paper explains the 'table-chart gap' in scientific claim verification by showing that multimodal LLMs successfully encode information from charts but fail to route it to the final prediction layer…

The paper introduces TorchSight, an open-source local system using a fine-tuned Qwen 3.5 27B model that achieves high accuracy (95.0%) in classifying sensitive security documents without relying on ex…

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.

The paper addresses 'Template Collapse' in 3D CT report generation—where models generate generic reports—by proposing CLarGen, a decoupled framework that significantly improves clinical accuracy and d…

The paper introduces a structured benchmark (TGAD) showing that current text-guided anomaly detection models often overstate their language conditioning, as performance significantly degrades when the…

The paper introduces MechVQA, a comprehensive dataset and benchmark for mechanical drawing understanding, and proposes the MechVL model, which significantly improves Multimodal LLMs' performance on th…

The paper introduces a new benchmark for multi-target cross-lingual summarization (MTXLS) and proposes an activation steering method that significantly improves LLM performance by guiding the generati…

The paper introduces OpAI-Bench, a novel benchmark designed to study how AI authorship signals evolve and accumulate during the progressive co-editing process between humans and AI.

KidsNanny is a two-stage multimodal content moderation pipeline that achieves high accuracy and efficiency in detecting child safety threats, particularly excelling in text-embedded content.

The paper proposes Dynamic Adapter Routing (DAR), a novel method that significantly improves continual multimodal retrieval by adaptively selecting and merging specialized adapters.

This paper introduces CFMME, a comprehensive Chinese financial multimodal benchmark, and evaluates current Large Vision-Language Models (LVLMs), finding that while state-of-the-art models perform mode…

The paper proposes VLM3, a simple, scalable method that demonstrates standard Vision Language Models (VLMs) can natively learn 3D understanding by focusing on architectural simplicity and specific dat…