Tag
InSight-doc is an agentic visual perception framework for long-document understanding that adaptively allocates visual resolution during reasoning, reducing hallucination and inference latency while improving accuracy on document VQA benchmarks. The paper releases an 8B model, datasets, and code.
PerceptionBench is a benchmark designed to evaluate atomic visual perception capabilities of Multimodal Large Language Models (MLLMs), using a bottom-up taxonomy of ten atomic perceptual capabilities. Results across 16 frontier MLLMs show no model reaches 60% accuracy, indicating visual perception remains largely unsolved.
This paper introduces ActiveVision, a benchmark to evaluate active observation in multimodal large language models. Frontier models like GPT-5.5 and Claude Fable 5 perform poorly, solving only 10.6% and 3.5% of tasks respectively, compared to human 96.1%, highlighting a lack of iterative visual perception.
BBC reports on a test and research into training people to spot AI-generated deepfake faces by focusing on perceptual qualities like symmetry, proportionality, and expressiveness, using StyleGAN3.
PerceptionDLM introduces a multimodal diffusion language model that enables parallel region perception via structured attention masking and efficient prompting, achieving faster inference without sacrificing caption quality. Experiments show competitive performance with substantial speed improvements for multi-region perception tasks.
This paper proposes a staged training approach for vision-language models that separates visual perception, visual reasoning, and textual reasoning into distinct stages. The method improves visual reasoning accuracy while reducing reasoning trace length, demonstrating that stronger perception reduces the need for excessive reasoning.
This paper introduces WebEye, a benchmark for object localization requiring external knowledge resolution, and Pixel-Searcher, an agentic approach that connects search results to visual annotations.