用专用小模型融合架构，让AI高效完成复杂开发者任务。
Interfaze: The Future of AI is built on Task-Specific Small Models
- 将专用模型直接嵌入Transformer解码器，按需调用仅相关参数。
- 多项任务表现超通用模型，如OCR准确率达70.7%，代码生成准确率80.5%。
- 适合需要高精度、低延迟和可验证输出的开发者工具场景。
我们提出Interfaze，一种原生混合模型，通过共享嵌入空间将特定任务的深度神经网络（CNNs与DNNs）直接融合进Transformer解码器。专用感知编码器分别处理复杂多语言PDF的OCR、开放词汇的目标与图形界面（GUI）检测、以及带说话人分离的多语言语音识别。每个模块通过任务适配器独立激活，查询仅触发所需参数。内置行动基础提供接地外部状态：代理无头浏览器与爬虫、代码沙箱、多领域网页索引及可扩展向量存储。解码器过滤并融合这些信号，在任务需要时进行推理，并生成基于置信度的确定性输出。原始专业元数据（边界框、置信度分数、时间戳）与答案一同返回作为预上下文。在一系列确定性开发者任务基准测试中，Interfaze-Beta表现领先：OCR Bench v2达70.7%，olmOCR为85.7%，RefCOCO为82.1%，VoxPopuli词错率为2.4%，Spider-2.0-Lite为52.9%，GPQA-Diamond为92.4%，MMMLU为90.9%，MMMU-Pro为71.1%，结构化输出基准（SOB）价值准确率为80.5%，优于同等价位通用模型（Gemini-3-Flash、Gemini-3.5-Flash、Claude-Sonnet-4.6、GPT-5.4-Mini、Grok-4.3）。由于融合的专用编码器在单次遍历中完成感知，而非依赖反复调用大模型工具，Interfaze在确定性任务上实现高精度与可验证元数据，同时保持闪速级成本。
原文摘要 · Abstract (English)
We present Interfaze, a native hybrid model that fuses task-specific deep neural networks (CNNs and DNNs) directly into a transformer decoder through a shared embedding space. Specialized perceptual encoders handle optical character recognition (OCR) over complex multilingual PDFs, open-vocabulary object and graphical user interface (GUI) detection, and multilingual speech recognition with diarization. Each is exposed through a task-specific adapter and can be activated on its own, so a query touches only the parameters it needs. A built-in action foundation supplies a grounded external state: a proxied headless browser and scraper, a code sandbox, a multi-domain web index, and a scalable vector store. The decoder filters and merges these signals, reasons over them when a task requires it, and emits deterministic outputs built on confidence. The raw specialist metadata (bounding boxes, confidence scores, timestamps) is preserved and returned alongside the answer as precontext. On this architecture, Interfaze-Beta leads a suite of deterministic developer-task benchmarks. It reaches 70.7% on OCRBench v2, 85.7% on olmOCR, 82.1% on RefCOCO, a 2.4% word error rate on VoxPopuli, 52.9% on Spider-2.0-Lite, 92.4% on GPQA-Diamond, 90.9% on MMMLU, 71.1% on MMMU-Pro, and 80.5% value accuracy on the Structured Output Benchmark (SOB), ahead of comparably priced generalist models (Gemini- 3-Flash, Gemini-3.5-Flash, Claude-Sonnet-4.6, GPT-5.4-Mini, and Grok-4.3) on every task. Because fused specialist encoders resolve perception in a single pass instead of through repeated tool calls into a large model, Interfaze reaches high accuracy with verifiable metadata on deterministic tasks while running at flash-tier cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。