Byte's MegaScale System Successfully Built for Large-Scale Card Clusters, Efficiently Completing GPT-3 Training

ByteDance Volcano Booth Officially Integrates DeepSeek-R1-0528 Version

Recently, ByteDance's Volcano Engine Large Model Service Platform, Volcano Ark, officially announced the integration of the latest version of DeepSeek-R1-0528. This move not only demonstrates ByteDance's technical strength in the field of large model services but also provides more efficient and convenient large model application experiences for enterprise users and developers. The Volcano Ark platform has built a high-performance service system targeting the core requirements of large model applications, namely speed and stability. By using its self-developed xLLM high-performance inference framework, the platform achieves a model latency as low as 30ms per T.

AI Daily: DeepSeek releases new version R1-0528; ByteDance releases image Agent Xiaoyunque AI; Keeling 2.1 is officially launched

ByteDance Releases Image Agent Xiaoyunque AI to Create a One-Click Hit Creation Tool

Today, ByteDance launched the new image agent "Xiaoyunque AI", an intelligent creation tool that has drawn industry attention. Its functions are similar to Lovart; users just need to give one instruction, and "Xiaoyunque AI" can actively think, intelligently execute, and quickly generate hit videos and images, truly achieving instant inspiration and zero-threshold creation. "Xiaoyunque AI" requires no professional skills, making creation as easy as chatting. It is suitable for short video creators, marketing teams, and ordinary users, greatly lowering the threshold of content creation. Relying on ByteDance's self-developed "Yunque" large model, this tool

ByteDance Launches New AI Video Editing App Jian Xiao Ying to Easily Record Life Moments

Trae International Version Launches Paid Subscription Model, First Month Pro Subscription Only $3 with Claude4 Support

Trae, as an AI-driven Integrated Development Environment (IDE) launched by ByteDance, has quickly gained prominence in the global developer community after its release on January 20, 2025, thanks to its powerful AI functionalities and seamless development experience. Recently, the international version of Trae officially rolled out a paid subscription strategy, marking its transition from completely free to a sustainable business model. This report was compiled by AIbase based on the latest online information, providing you with a detailed understanding of the specifics of Trae's international version subscription strategy and its potential impact on developers.

AI Daily: Kunlun WonderWorks TianGong Super Intelligent APP Launched; Google Releases Three Major Variants of Gemma Model; ByteDance Launches Open-Source Multimodal Model BAGE

Welcome to the 【AI Daily】 column! This is your guide to exploring the world of artificial intelligence every day. Here we bring you hot content in the AI field, focusing on developers to help you gain insights into technical trends and understand innovative AI product applications. Fresh AI products click to learn more: https://top.aibase.com/1. The world's first Office intelligent agent APP! Kunlun Wonderworks TianGong Super Intelligent APP launched by Kunlun WonderWorks Group.

ByteDance Releases Open Source Multi-modal Model BAGE From Image Generation to World Modeling

ByteDance recently officially released its latest open source multi-modal foundation model - BAGEL (Big Advanced Generalized Embodied Learner), starting a new stage for multi-modal AI models with a scale of 7 billion effective parameters. BAGEL performs excellently in key tasks such as image understanding, generation, and editing, and has surpassed current mainstream open source vision-language models (VLM) like Qwen2.5-VL and InternVL-2.5 in multiple standard evaluations.

AI Daily: Anthropic推出了最强编码 AI model Claude4; Apple plans to release AI smart glasses; ByteDance and Tsinghua jointly release multi-modal large model ChatTS

ByteDance and Tsinghua University Collaborate to Launch ChatTS, a Temporal Multimodal Large Model

ByteDance releases 14B parameter multi-modal powerhouse BAGEL, outperforms Qwen2.5-VL in image generation媲美SD3