ZhiYuan Research Institute Releases Emu2: A New Generation Generative Multimodal Foundation Model

站长之家

Published inAI News · 2 min read · Dec 22, 2023

135

The Beijing Academy of Artificial Intelligence (BAAI) has released Emu2, a new generation of multi-modal foundational models. Through extensive autoregressive generative multi-modal pre-training, Emu2 has significantly advanced the breakthroughs in multi-modal contextual learning capabilities. Emu2 excels in few-shot multi-modal understanding tasks, surpassing mainstream multi-modal pre-training models like Flamingo-80B and IDEFICS-80B. It has achieved optimal performance in multiple few-shot understanding, visual question answering, and image generation tasks. Emu2-Chat can accurately comprehend text-image instructions, enabling better information perception, intent understanding, and decision planning. Emu2-Gen can accept sequences of interleaved images, text, and locations as input, achieving flexible, controllable, and high-quality image and video generation. Emu2 adopts a simpler modeling framework and scales the model up to 37 billion parameters. For more details, please refer to the project link released by BAAI.

Baidu and Zhiyuan Research Institute Reach Strategic Agreement to Collaborate in Large Model and Other Fields

Beijing Baidu Network Technology Co., Ltd. and Beijing Zhiyuan Artificial Intelligence Research Institute announced today the formal signing of a strategic cooperation agreement, under which the two sides will engage in deep collaboration in large model and other fields, jointly constructing an AI industry-research collaborative ecosystem. Baidu has been comprehensively laying out its artificial intelligence strategy since 2010 and is one of the few companies globally that has fully integrated its AI efforts, from Kunlun chips, PaddlePaddle deep learning platform, Wenxin large model to applications.

ZhiYuan Research Institute Launches FlagEval Large Model Arena Featuring Text-to-Video Model Combat Evaluation Service

On September 4, 2024, the Beijing ZhiYuan Artificial Intelligence Research Institute (BAAI) announced the launch of the world's first model combat evaluation service featuring text-to-video, called FlagEval Large Model Arena. This service is open to users and covers approximately 40 large models from both domestic and international sources, supporting customizable online or offline evaluations for four major tasks: language Q&A, multimodal image and text understanding, text-to-image, and text-to-video.

Zhiyuan Releases Three New BGE Models, Setting New Best Standards in Vector Retrieval

The Zhiyuan Research Institute recently released three new vector models that excel in vector retrieval tasks and have set new best standards across multiple evaluation benchmarks. The three models are: BGE-EN-ICL: an English vector model that enhances the model's semantic expression capabilities by introducing task-related query-document examples as few-shot examples.

Zhiyuan Research Institute Releases the World's First Trillion-Parameter Dense Model Tele-FLM-1T as Open Source

Beijing Zhiyuan Artificial Intelligence Research Institute, in collaboration with China Telecom Artificial Intelligence Research Institute, has launched an upgraded version of the Tele-FLM series of large models, including the 52B instruction model FLM-2-52B-Instruct and the trillion-parameter model Tele-FLM-1T. The FLM-2-52B-Instruct focuses on enhancing Chinese conversational abilities through instruction fine-tuning, achieving 90% of GPT-4's capabilities, based on the Tele-FLM-52B base model, utilizing specific datasets and parameter optimization.