研究人员推出了 M$^3$-VQA，这是一个新的基准，旨在评估多模态大语言模型 (MLLMs) 在涉及多个实体和多跳推理的复杂推理任务上的表现。该基准挑战模型理解跨越视觉和文本来源的细粒度细节，需要顺序和并行推理。对 16 个领先的 MLLMs 的初步评估显示，它们在知识获取和推理能力方面存在显著局限性，尽管在提供精确证据时性能有了实质性提高。 AI
影响 该基准将通过突出当前局限性来推动大语言模型多模态推理的进步。
排序理由 引入了一个新的基准来评估多模态大语言模型。
AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →
arXiv:2604.28039v1 Announce Type: new Abstract: Spectra are a prevalent yet highly information-dense form of scientific imagery, presenting substantial challenges to multimodal large language models (MLLMs) due to their unstructured and domain-specific characteristics. Here we in…
Spectra are a prevalent yet highly information-dense form of scientific imagery, presenting substantial challenges to multimodal large language models (MLLMs) due to their unstructured and domain-specific characteristics. Here we introduce SpecVQA, a professional scientific-image…
arXiv:2604.23443v1 Announce Type: new Abstract: Stochastic sampling strategies are widely adopted in large language models (LLMs) to balance output coherence and diversity. These heuristics are often inherited in Multimodal LLMs (MLLMs) without task-specific justification. Howeve…
We present M$^3$-VQA, a novel knowledge-based Visual Question Answering (VQA) benchmark, to enhance the evaluation of multimodal large language models (MLLMs) in fine-grained multimodal entity understanding and complex multi-hop reasoning. Unlike existing VQA datasets that focus …
arXiv:2604.25122v1 Announce Type: new Abstract: We present M$^3$-VQA, a novel knowledge-based Visual Question Answering (VQA) benchmark, to enhance the evaluation of multimodal large language models (MLLMs) in fine-grained multimodal entity understanding and complex multi-hop rea…
We present M$^3$-VQA, a novel knowledge-based Visual Question Answering (VQA) benchmark, to enhance the evaluation of multimodal large language models (MLLMs) in fine-grained multimodal entity understanding and complex multi-hop reasoning. Unlike existing VQA datasets that focus …