Search AI Products and News

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.

Alibaba is making waves in the AI field with the recent open-source release of its latest multimodal model, Qwen2.5-VL-32B-Instruct. This model is part of the Qwen2.5 series, which also includes 3B, 7B, and 72B versions. The 32B version prioritizes convenient local execution while maintaining performance. Enhanced through reinforcement learning, Qwen2.5-VL-32B excels in several areas. Notably, its responses are more aligned with human expectations.

Google CEO Sundar Pichai announced at a launch event that Google has open-sourced its latest multimodal large model, Gemma-3. This model is attracting significant attention for its low cost and high performance. Gemma-3 offers four different parameter scale options: 1 billion, 4 billion, 12 billion, and 27 billion parameters. Surprisingly, the largest 27 billion parameter model only requires a single H100 GPU for efficient inference, while similar models often require ten times the computing power.

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...

Recently, the Modelers community officially launched Step-Video and Step-Audio, two open-source multimodal large models developed by Step-Star. These models are designed for video generation and voice interaction, respectively, aiming to provide developers and enterprise users with more powerful AI tools. Step-Video, formally known as Step-Video-T2V, is a 30-billion parameter model, making it the world's largest open-source video generation model. This model can directly generate 20...

Beijing Zhipu Huazhang Technology Co., Ltd. announced that its Zhipu Open Platform BigModel has launched the first free multimodal API—GLM-4V-Flash. This new model leverages the excellent capabilities of the 4V series, achieving improved accuracy in image processing and further lowering the barriers for developers to delve deeper into large models across various fields.

Zhipu Technology recently announced the open source of its end-side large language and multimodal model GLM-Edge series, marking an important attempt by the company in real-world use cases at the end side. The GLM-Edge series consists of four different model sizes, including GLM-Edge-1.5B-Chat, GLM-Edge-4B-Chat, GLM-Edge-V-2B, and GLM-Edge-V-5B, which are optimized for mobile platforms such as smartphones and vehicle systems, as well as desktop platforms like PCs.

Recently, research teams from Peking University announced the release of an open-source multimodal model called LLaVA-o1, which is claimed to be the first visual language model capable of spontaneous and systematic reasoning, comparable to GPT-o1. The model excels in six challenging multimodal benchmark tests, with its 11B parameter version outperforming competitors such as Gemini-1.5-pro, GPT-4o-mini, and Llama-3.2-90B-Vision-Instruct.

Recently, an open source multimodal AI model named Molmo has drawn widespread attention in the industry. This AI system, based on Qwen2-72B and leveraging OpenAI's CLIP as the visual processing engine, is challenging the dominance of traditional commercial models with its outstanding performance and innovative features. Molmo's standout characteristic is its efficient performance. Despite its relatively small size, it can compete with competitors that are ten times larger in processing capability. This 'small but exquisite' design philosophy not only enhances the model's

The latest version 2.6 of WallFacer’s MiniCPM-V series has rapidly climbed to the Top 3 on GitHub and HuggingFace trends, surpassing ten thousand stars. Since its release in February, it has accumulated over a million downloads, becoming a benchmark for on-device model capabilities. MiniCPM-V2.6 achieves performance enhancements for on-device multimodal models with 8 billion parameters, including real-time video understanding, multi-image joint understanding, and multi-image in-context learning, with a quantized backend memory of only 6GB and an inference speed of up to 18 tokens.

Google has released its latest AI masterpiece, Gemini 1.5 Pro, offering an experimental version 0801 through Google AI Studio and the Gemini API. This model leads the LMSYS leaderboard with an ELO score of 1300, surpassing OpenAI's GPT-4o and Anthropic's Claude-3.5 Sonnet. Gemini 1.5 Pro excels in multilingual tasks, mathematics, coding, and visual tasks, featuring a context window of 2 million tokens.

Shusheng · Puyu Lingbi (InternLM-XComposer) Version 2.5 was developed by the Shanghai Artificial Intelligence Laboratory, focusing on long context input and output capabilities, operating smoothly within a length of 96K, and trained with 24K interleaved image-text data. Key upgrades include: high-resolution image understanding, fine-grained video understanding, and multi-turn multi-image dialogue. In application, it can create web pages and write high-quality text-image articles. Evaluations show it surpasses state-of-the-art open-source models across 16 benchmark tests and performs at par with key tasks compared to GPT-4V and Gem.