Search AI Products and News

ByteDance's AI-powered assistant app, Doubao, recently announced a new feature called "Bring Photos to Life." This feature aims to meet users' needs for animating old photos, breathing new life into cherished memories. The process is reportedly simple: users open the Doubao app, select the feature, upload an old photo, and describe the actions of the people or objects in the photo. After a short wait, Doubao uses advanced AI technology to transform the static image into a lively animation.

Amidst the anticipation of numerous users, Byte's AI programming tool Trae has officially announced support for the Win x64 version and emphasized that this update will bring a smoother operating experience for Win x64 users. Trae, as a highly adaptable AI Integrated Development Environment (IDE), is quickly becoming the ideal choice for developers. It not only enables seamless collaboration with users but also significantly enhances work efficiency, making the development process easier and more enjoyable. The Builder mode of Trae is one of its major highlights.

On December 5th, the Byte Bean Bag model team launched the latest code model evaluation benchmark - FullStack Bench, covering over 11 real-world scenarios, supporting 16 programming languages, and including 3374 questions. Compared to previous evaluation standards, this benchmark can more accurately assess the code development capabilities of large models across a broader programming domain, facilitating the optimization of models in real-world programming tasks. Current mainstream code evaluation benchmarks, such as HumanEval and MBPP, typically focus on basic and advanced.

Recently, researchers from ByteDance Research Institute and Tsinghua University jointly released a new study, pointing out that current AI video generation models, such as OpenAI's Sora, while capable of creating stunning visual effects, have significant flaws in understanding basic physical laws. This study has sparked widespread discussion on the capabilities of AI in simulating reality. The research team tested AI video generation models under three different scenarios: predictions under known patterns and predictions under unknown patterns.

ByteDance launched its latest image editing model, SeedEdit, on November 11, becoming the first productized universal image editing tool in China. Users can simply input a straightforward natural language instruction to change the background, transform styles, and add or remove elements in images, without the need for complex tracing and painting. SeedEdit excels at understanding commands, accurately interpreting both Chinese and English prompts, including idioms and proper nouns. For example, a user can just input 'replace the watermelon with grapes,' and SeedEdit...

At the Volcano Engine AI Innovation Roadshow in Shanghai on August 21, 2024, Volcano Engine showcased a comprehensive upgrade of the Doubao Large Model. This includes the Doubao Text-to-Image Model, which has improved text and image matching capabilities for long texts, the Doubao Speech Recognition Model, which reduced error rates by up to 40% across multiple public test sets, and upgrades to the Doubao Speech Synthesis Model, enhancing streaming speech synthesis abilities for real-time responses and accurate punctuation. Volcano Engine also released a real-time interactive solution for Conversational AI, integrating the Doubao Large Model with real-time audio and video technology, providing end-to-end capabilities.

Sponge Music is an AI-based music creation tool designed to simplify the music production process, enabling everyone to easily realize their musical dreams. By simply inputting inspiration or lyrics, the AI generates music works, providing a convenient creation method and rich customization features that support various music styles and adjustment options. Sponge Music supports two creation modes: Inspiration Creation and Custom Creation, allowing users to input ideas or lyrics and select genres, moods, and timbres, generating music with one click. Testing shows that the music generated in Custom Creation mode yields good results, and Chinese processing can...

Recently, Honor Mobile announced a collaboration with Doubao Model under Byte. According to official news from Volcano Engine, several models from the Doubao Model family, including voice recognition and role-playing, will provide foundational capabilities to support Honor in building vertical model applications in the mobile office field.

Recently, Xiaomi's AI assistant 'Xiao Ai' has collaborated with ByteDance's Volcano Engine, utilizing the latter's large language model 'Doubao' to provide users with a more intelligent AI interaction experience.

Byte has launched 7 new products in half a year, raising questions about whether it can shine in the market during the AI era. Byte's commitment to technological innovation and its developments are drawing significant attention.

Byte's large model BuboGPT supports fine-grained multimodal joint understanding of text, images, and audio. By introducing a visual localization method, BuboGPT can accurately locate objects in images. Researchers have utilized a multimodal instruction tuning training scheme, achieving good results on multimodal tasks.