InfiX.ai

助力生成式人工智能的
最后一公里

我们的使命与愿景

InfiX.ai 正在通过低精度训练、模型融合、GUI 智能体和多模态智能，开创协作式生成 AI 的新路径

使命

在 InfiX.ai，我们致力于让 AI 更易获取、更高效、更强大。我们的研究专注于开发创新技术，在保持实际可用性的同时，不断突破 AI 系统所能实现的边界。

愿景

我们不只是在构建又一个模型，而是正在构建能够构建所有模型的系统。

研究重点

推理增强型低精度训练

降低训练时间、内存压力和推理成本，提升模型训练与部署效率。在保持接近 BF16 精度的同时，实现最高 22% 的训练时间缩短和 19% 的吞吐量提升。

模型融合与模型合并

将多个模型的优势融合为更强的专家级 AI，同时无需承担多模型推理的额外开销。支持跨多领域的百亿参数级基础模型融合，所需 GPU 算力仅为完整预训练的万分之一。

推理增强型低精度训练

降低训练时间、内存压力和推理成本，提升模型训练与部署效率。在保持接近 BF16 精度的同时，实现最高 22% 的训练时间缩短和 19% 的吞吐量提升。

模型融合与模型合并

将多个模型的优势融合为更强的专家级 AI，同时无需承担多模型推理的额外开销。支持跨多领域的百亿参数级基础模型融合，所需 GPU 算力仅为完整预训练的万分之一。

最新研究

2026年4月30日

BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models

Large language model inference is often bounded by memory footprint and memory bandwidth in resource-constrained deployments, making quantization a fundamental technique for efficient serving. While post-training quantization maintains high fidelity at 4-bit, it deteriorates at 2-3 bits. BPDQ constructs a variable quantization grid via bit-planes and scalar coefficients, then iteratively refines them with approximate second-order information and progressive error compensation to minimize output discrepancy. In the 2-bit regime, BPDQ enables serving Qwen2.5-72B on a single RTX 3090 with 83.85% GSM8K accuracy, compared with 90.83% at 16-bit.

2026年4月30日

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training

ORBIT is an open-ended rubric-based incremental training framework for high-stakes medical dialogue. It combines synthetic dialogue generation, retrieval-augmented rubric construction, difficulty filtering, and rubric-guided reinforcement learning to align LLMs on context-dependent consultation tasks. Applied to Qwen3-4B-Instruct, ORBIT raises the HealthBench-Hard score from 7.0 to 27.5 using only 2k training samples, with larger rubric sets improving performance to 33.6 and 37.3.

2026年4月30日

Model Merging Scaling Laws in Large Language Models

This work studies empirical scaling laws for language model merging measured by cross-entropy. Across 10,866 merged models, base sizes from 0.5B to 72B, nine domains, and four methods, the paper identifies a compact floor-plus-tail power law that links model size and expert count. The law explains why most merging gains arrive early, why variability shrinks as more experts are included, and how to plan expert count under a budget.

查看所有研究