Search AI Products and News

Recently, the Qwen VLo multimodal large model was officially released, achieving significant advancements in image content understanding and generation, offering users a brand-new visual creation experience. According to the introduction, Qwen VLo has been comprehensively upgraded based on the advantages of the original Qwen-VL series models. The model not only can accurately understand the "world", but also can perform high-quality re-creation based on understanding, truly achieving the transition from perception to generation. Users can now access Qwen Chat (chat.qwen.ai)

Welcome to AIbase's [AI Daily Report]! Spend three minutes every day to learn about the latest AI news, helping you understand AI industry trends and innovative AI product applications. For more AI updates, visit: https://www.aibase.com/zh1. Tencent open-sources the lightweight Huyuan-A13B model, which can be deployed with just one mid-range GPU card. Tencent has released a new member of the Huyuan large model family, the Huyuan-A13B model, which uses a mixture of experts (MoE) architecture, with a total parameter scale of 80 billion and an activated parameter count of 13 billion, large

Recently, the innovative AI company Vibemotion launched a revolutionary AI dynamic graphics platform, aiming to allow users to easily create high-quality dynamic videos through simple prompts and material input. Currently, the platform is available by invitation only, attracting widespread global attention from content creators. AIbase provides an in-depth analysis of the platform's key features and its potential impact on the creative industry. One-click generation of dynamic videos, lowering the creation threshold to a new low. The core of Vibemotion's AI dynamic graphics platform lies in its extremely simple user experience.

With the continuous progress of artificial intelligence technology, multimodal data processing has gradually become a popular topic. Recently, the globally renowned electrical appliances brand Panasonic launched its latest R&D multimodal large model — OmniFlow. This model can efficiently convert between multiple modalities such as text, image, and audio, achieving any-to-any generation tasks, providing users with a more flexible experience. The design concept of OmniFlow is based on modularity, allowing the various components of the model to be independently pre-trained. This approach not only improves training efficiency but also avoids...

The British Film Institute (BFI) recently released a重磅 report indicating that generative AI is quietly reshaping the UK's film, television, and gaming industries. The technology has been widely used backstage to enhance production efficiency and spur new creative approaches and business models. The report shows that generative AI has been utilized to accelerate scriptwriting, character modeling, visual effects creation, and more, significantly saving time and costs. Some works have even employed AI assistance for pre-production conceptualization and editing decisions, empowering creativity while allowing small and medium-sized production companies to benefit.

The AI visual generation platform Higgsfield has launched another major feature - "Speak", bringing unprecedented convenience to digital human content creators. Users only need three steps: select preset actions, upload custom roles, and input voice text, to generate digital human videos with lip-sync and natural actions. The Speak feature supports precise lip-sync technology, ensuring that the character's pronunciation is natural and synchronized, along with 16 built-in scene types covering diversified content styles such as interviews, explanations, advertisements, and short plays, greatly enhancing creation.

Recently, the Beijing Academy of Artificial Intelligence (BAEI), in collaboration with Shanghai Jiao Tong University and other institutions, officially released a new generation of ultra-long video understanding model - Video-XL-2. The introduction of this model represents a significant breakthrough in the field of open-source ultra-long video understanding technology, injecting new vitality into the development of multimodal large models for understanding long video content. In terms of technical architecture, Video-XL-2 mainly consists of three core components: a visual encoder, the Dynamic Token Synthesis (DTS) module, and a large language model (LLM). The model adopts

Recently, the Natural Language Intelligence Team of the Tongyi Lab officially released and open-sourced VRAG-RL — a multi-modal RAG reasoning framework driven by visual perception. It aims to solve the problem of how AI can retrieve key information and conduct fine-grained reasoning from visual languages such as images, tables, design drafts, etc., in real-world business scenarios. Retrieving and reasoning about key information in complex visual document knowledge bases has always been a major challenge in the AI field. Traditional retrieval-augmented generation (RAG) methods struggle when handling visually rich information because they find it difficult to...

Recently, the Speech Team of Qwen Laboratory has made a milestone achievement in the field of spatial audio generation and launched the OmniAudio technology. This technology can directly generate FOA (First-order Ambisonics) audio from 360-degree videos, bringing new possibilities to virtual reality and immersive entertainment. Spatial audio, as a technology that simulates real auditory environments, can enhance immersive experiences. However, existing technologies are mostly based on fixed perspective videos and underutilize the spatial information of 360-degree panoramic videos. Traditional video-to-audio generation

Recently, Qwen released CoGenAV, innovating speech recognition technology with the concept of audio-visual synchronization. It effectively addresses the challenge of noise interference in speech recognition. Traditional speech recognition performs poorly in noisy environments, while CoGenAV takes a different approach by learning the temporal alignment relationships among audio-visual-text, building a more robust and generalizable speech representation framework, systematically improving tasks such as speech recognition (VSR/AVSR), speech reconstruction (AVSS/AVSE), and audio-visual synchronization (A').

Recently, a new evaluation benchmark - RBench-V, specifically designed to test the visual reasoning capabilities of multi-modal large models, was released by research teams from Tsinghua University, Tencent HUNYUAN, Stanford University, and Carnegie Mellon University. The introduction of this benchmark aims to fill the gap in the current evaluation system regarding the model's visual output capabilities, allowing for a more comprehensive understanding of existing model performance. The RBench-V benchmark consists of 803 questions covering multiple fields, including geometry and graph theory, mechanics and electromagnetism, multi-target recognition, and path planning.

The official DouBao account has officially announced the launch of a real-time video call function on the DouBao App. The introduction of this new feature brings users an entirely new interactive experience. Once users activate the video interface in the DouBao App call screen, DouBao can conduct real-time question-and-answer interactions with users based on the actual scenario. The underlying model integrates visual and language input capabilities, allowing for comprehensive deep thinking and creation.