Search AI Products and News

On June 23, NetEase Youdao officially launched and open-sourced its latest 'Ziyue 3' series large model, named 'Confucius3-Math' in English. This reasoning model, focused on mathematical education, can efficiently run on ordinary consumer-grade GPUs, becoming the first low-cost and high-performance AI educational tool in China. In a series of mathematical reasoning tasks, 'Ziyue 3' has demonstrated outstanding performance that surpasses many large-scale general models. The 'Ziyue Math Model' achieves this through large-scale reinforcement learning and a series of innovative algorithms.

A recent joint study by Google, Carnegie Mellon University, and MultiOn explores the application of synthetic data in training large language models. According to Epoch AI, a research institution focused on AI development, currently available high-quality text training data totals around 300 trillion tokens. However, with the rapid advancement of large models like ChatGPT, the demand for training data is growing exponentially, projected to exhaust existing resources by 2026. Therefore, synthetic data is becoming increasingly crucial.

On March 27th, Alibaba launched its first multimodal large model, Qwen2.5-Omni-7B. This model boasts powerful capabilities, handling various input modalities such as text, images, audio, and video, and generating text and natural speech outputs in real-time. This innovative technological breakthrough marks another significant advancement for Alibaba in the field of artificial intelligence. In the authoritative OmniBench multimodal fusion task benchmark, Qwen2.5-Omni achieved...

The Alibaba Cloud Tongyi Qianwen Qwen team announced the launch of Qwen2.5-Omni, a new generation of end-to-end multimodal flagship model in the Qwen family. Designed for comprehensive multimodal understanding, this new model seamlessly handles various input formats including text, images, audio, and video, and generates text and natural speech synthesis outputs simultaneously via real-time streaming response.

On March 11th, the Tongyi Lab team announced the open-sourcing of the R1-Omni model, marking a significant advancement in multimodal model development. This model integrates reinforcement learning with verifiable reward (RLVR) methods, focusing on improving reasoning capabilities and generalization performance in multimodal emotion recognition tasks. R1-Omni's training is divided into two stages. In the cold-start phase, the team fine-tuned the model using a combined dataset containing 580 video clips sourced from Explainable Multimodal Emotion...

On March 6, 2025, a new language model called **Light-R1-32B** was officially launched. Built upon the **Qwen2.5-32B-Instruct** model, this mathematical problem-solving tool, specially trained for exceptional mathematical abilities, low training costs, and reproducibility, is a significant highlight in the field of artificial intelligence. The development team xAI stated that Light-R1-32B not only surpasses similar models in performance but also provides significant benefits for academic research and practical applications.

Today, the Alibaba Cloud Tongyi team officially released the new mathematical reasoning process reward model Qwen2.5-Math-PRM. This model offers two sizes, 72B and 7B, with performance significantly outperforming similar open-source process reward models, especially excelling in identifying reasoning errors. The 7B version of Qwen2.5-Math-PRM astonishingly surpasses the widely popular GPT-4o, marking an important step in Alibaba Cloud's research and development of reasoning models.

Today, iFLYTEK Spark 4.0 Turbo has undergone a comprehensive upgrade, with significant improvements in its seven core capabilities—text generation, language understanding, knowledge Q&A, logical reasoning, mathematical ability, coding ability, and multimodal ability—surpassing the powerful performance of GPT-4o in math and coding.

Domestic artificial intelligence company Wenwen Xinqun has announced the open sourcing of its latest developed end-side full-modal understanding AI model — Megrez-3B-Omni. This model is the world's first open source project of its kind, marking the company's innovative development in the AI field. At the same time, Wenwen Xinqun also launched a pure language version of the model, Megrez-3B-Instruct, to further enrich its product line. Founded in May 2023, the founding team comes from the Department of Electronic Engineering at Tsinghua University. The company is committed to creating efficiency.

DeepSeek AI recently launched DeepSeek-V2.5-1210, an enhanced version of DeepSeek-V2.5, aimed at improving AI performance in math, programming, writing, and reasoning tasks. Earlier versions of the model achieved some success in solving math and reasoning tasks, but the stability of performance across various applications needed enhancement, especially in real-time coding and meticulous writing. These shortcomings underscore the potential for developing a more flexible and reliable AI model.