Search AI Products and News

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.

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, 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.

Tencent officially released the H混元 Game Visual Generation Platform, which is an AI content engine built on the H混元 large model, specifically designed for industrial-level content production in the gaming industry. The launch of this platform marks the entry of the game art design industry into a new era of efficient creation, expected to increase creation efficiency by tens of times. In the past, game art designers often had to jump between multiple software when creating character images, from finding reference images to drafting sketches, making three-view drawings, and creating dynamic demonstrations, the entire process was scattered and cumbersome, with files requiring repeated imports and exports.

In the field of artificial intelligence, Meta recently introduced the WebSSL family of models. These models, ranging in size from 300 million to 7 billion parameters, are trained on purely image data and aim to explore the vast potential of language-free visual self-supervised learning (SSL). This new research opens up new possibilities for future multimodal tasks and offers a fresh perspective on understanding how visual representations are learned. Previously, OpenAI's CLIP model was known for its performance in multimodal tasks such as visual question answering (VQA) and document understanding.

On April 24th, Kunlun Wanwei announced the official open-sourcing of its multimodal reasoning model, Skywork-R1V2.0 (hereinafter referred to as R1V2.0). This upgraded version demonstrates significant improvements in both visual and text reasoning capabilities, particularly excelling in deep reasoning for challenging science problems in the College Entrance Examination and general task scenarios. It is considered the currently most balanced open-source multimodal model, equally adept at visual and text reasoning.