Firebolt-VL: 通过跨模态调制实现高效的视觉-语言理解
Firebolt-VL: Efficient Vision-Language Understanding with Cross-Modality Modulation
AI总结：
本文提出Firebolt-VL模型，通过替换Transformer解码器为液态基础模型解码器，并引入Token-Grid相关模块，提升视觉语义理解效率与精度。
摘要：
近年来，多模态大语言模型（MLLMs）在视觉-语言理解方面取得了显著进展，但其高计算成本限制了在资源受限场景中的应用。现有方法依赖于基于Transformer的交叉注意力机制，其二次复杂度阻碍了效率。此外，小型视觉-语言模型难以精确捕捉细粒度、任务相关的视觉区域，导致在细粒度推理任务中的性能下降。为此，我们引入Firebolt-VL，一种高效的视觉-语言模型，用液态基础模型（LFM）解码器替代基于Transformer的解码器。为进一步增强视觉语义，我们提出Token-Grid相关模块，通过状态空间模型与FiLM条件调制计算文本标记与图像块之间的轻量级相关性。这使模型能够选择性地强调与文本提示相关的视觉区域，同时保持线性时间推断。在多个基准测试中，Firebolt-VL实现了准确的细粒度理解，并显著提高了效率。我们的模型和代码可在https://fireboltvl.github.io获取。
英文摘要：
Recent advances in multimodal large language models (MLLMs) have enabled impressive progress in vision-language understanding, yet their high computational cost limits deployment in resource-constrained scenarios such as personal assistants, document understanding, and smart cameras. Most existing methods rely on Transformer-based cross-attention, whose quadratic complexity hinders efficiency. Moreover, small vision-language models often struggle to precisely capture fine-grained, task-relevant visual regions, leading to degraded performance on fine-grained reasoning tasks that limit their effectiveness in the real world. To address these issues, we introduce Firebolt-VL, an efficient vision-language model that replaces the Transformer-based decoder with a Liquid Foundation Model (LFM) decoder. To further enhance visual grounding, we propose a Token-Grid Correlation Module, which computes lightweight correlations between text tokens and image patches and modulates via the state-space model with FiLM conditioning. This enables the model to selectively emphasize visual regions relevant to the textual prompt while maintaining linear-time inference. Experimental results across multiple benchmarks demonstrate that Firebolt-VL achieves accurate, fine-grained understanding with significantly improved efficiency. Our model and code are available at: https://fireboltvl.github.io
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
