We present LLaMA-Adapter, a lightweight adaption method to efficiently fine-tune LLaMA
into an instruction-following model. Using 52K self-instruct demonstrations, LLaMA-Adapter …

How to efficiently transform large language models (LLMs) into instruction followers is
recently a popular research direction, while training LLM for multi-modal reasoning remains …

With the rising tide of large language models (LLMs), there has been a growing interest in
developing general-purpose instruction-following models, eg, ChatGPT. To this end, we …

以扩散模型和经扩散模型训练而成的海量的, 个性化的预训练模型和微调模型为代表的图像生成
式AI 在图像生成, 修改与替换等领域一枝独秀. 核心技术开源,“一键式” 便捷操作并且兼顾“质” …

This bachelor thesis evaluates Conditional Diffusion Models, a rapidly emerging class of
Generative Models. Although Conditional Diffusion Models have a wide range of …

In task-oriented conversational AI evaluation, unsupervised methods poorly correlate with
human judgments, and supervised approaches lack generalization. Recent advances in …

Generative AI is a hot topic as of 2023, with huge financial investments in the industry. The
areas of use for it are rapidly expanding. One potential benefit of generative AI could be in …