To avoid losing contact, please also follow the backup account. Large language models are machine learning models capable of generating natural language text based on context. In recent years, with the development of deep learning and big data, the performance and capabilities of language models have significantly improved, leading to the emergence of many applications … Read more
Paper: https://arxiv.org/abs/2501.00888 Github: https://github.com/Alibaba-NLP/CHRONOS Demo: https://modelscope.cn/studios/vickywu1022/CHRONOS In the digital age, the exponential growth of news information makes it crucial to extract and organize historical event timelines from massive texts. To address this challenge, Alibaba’s Tongyi Lab and researchers from Shanghai Jiao Tong University proposed a new framework for news timeline summarization based on agents—CHRONOS, named … Read more
Today, I will share a retrieval-augmented generation method designed for resource-constrained scenarios: MiniRAG. Paper link: https://arxiv.org/pdf/2501.06713 Code link: https://github.com/HKUDS/MiniRAG Introduction With the rapid development of retrieval-augmented generation (RAG) technology, the performance of language models in knowledge retrieval and generation tasks has significantly improved. However, existing methods heavily rely on large language models (LLMs), leading to … Read more
Paper Title “AUTOPROMPT: Eliciting Knowledge from Language Models with Automatically Generated Prompts”, authored by Taylor Shin, Yasaman Razeghi, Robert L. Logan IV, Eric Wallace, and Sameer Singh. The paper was published at the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). The paper aims to enhance the performance of language models on downstream … Read more
Hello everyone, I am Xiaoshui! Today, I want to share my learning notes from the AI learning course “Everyone is a Prompt Engineer” by Geek Time, focusing on common design pitfalls in prompts. Now, let me share my experiences regarding some of the above pitfalls when using AI large language models. As a programmer, my … Read more
Follow the public account “ML_NLP” Set as “Starred”, heavy content delivered first time! Overview of this article: 1. Background Knowledge Word2Vec is a type of language model that learns semantic knowledge from a large amount of text data in an unsupervised manner, and is widely used in natural language processing. Word2Vec is a tool for … Read more
OpenRouter is an impressive free AI tool. When we develop using APIs from closed-source models like OpenAI and Claude, as well as open-source models like LLaMa, we often encounter differences among different vendors’ APIs. Therefore, when switching between different large model service providers, your code typically requires modifications. The purpose of OpenRouter is to encapsulate … Read more
“Most people never take a glance beyond this earthly world before they die.” — Liu Cixin, The Three-Body Problem In the process of learning and using new technologies, the yearning for new knowledge generates internal motivation. Internal motivation and interest are the two best teachers. When using large language models for writing, it is necessary … Read more
Source: ZHUAN ZHI This article is approximately 1000 words, recommended reading time is 5 minutes. We explore three paths to introduce language into computer vision systems for open set recognition. The visual world is vast and constantly evolving. Additionally, due to the long-tail nature of data collection, computer vision systems cannot observe all visual concepts … Read more
Lightning Attention-2 is a novel linear attention mechanism that aligns the training and inference costs of long sequences with those of a 1K sequence length. The limitations on sequence length in large language models significantly constrain their applications in artificial intelligence, such as multi-turn dialogue, long text understanding, and the processing and generation of multimodal … Read more