Alibaba’s Qwen Team Releases QVQ-72B Open Source Vision AI Model in Preview

Alibaba’s Qwen Team Releases QVQ-72B Open Source Vision AI Model in Preview

Alibaba’s Qwen research team has released another open-source artificial intelligence (AI) model in preview. Dubbed QVQ-72B, it is a vision-based reasoning model that can analyze visual information from images and understand the context behind them. The tech giant has also shared benchmark scores of the AI ​​model and highlighted that on one specific test, it was able to outperform OpenAI’s o1 model. Notably, Alibaba has released several open-source AI models recently, including the QwQ-32B and Marco-o1 reasoning-focused large language models (LLMs).Alibaba’s Vision-Based QVQ-72B AI Model LaunchedIn a Hugging Face listing, Alibaba’s Qwen team detailed the new open-source AI model. Calling it an experimental research model, the researchers highlighted that the QVQ-72B comes with enhanced visual reasoning capabilities. Interestingly, these are two separate branches of performance, that the researchers have combined in this model.Vision-based AI models are plenty. These include an image encoder and can analyze the visual information and context behind them. Similarly, reasoning-focused models such as o1 and QwQ-32B come with test-time compute scaling capabilities that allow them to increase the processing time for the model. This enables the model to break down the problem, solve it in a step-by-step manner, assess the output and correct it against a verifier.With QVQ-72B’s preview model, Alibaba has combined these two functionalities. It can now analyze information from images and answer complex queries by using reasoning-focused structures. The team highlights that it has significantly improved the performance of the model. Sharing evals from internal testing, the researchers claimed that the QVQ-72B was able to score 71.4 percent in the MathVista (mini) benchmark, outperforming the o1 model (71.0). It is also said to score 70.3 percent on the Multimodal Massive Multi-task Understanding (MMMU) benchmark.Despite the improved performance, there are several limitations, as is the case with most experimental models. The Qwen team stated that the AI ​​model occasionally mixes different languages ​​or unexpectedly switches between them. The code-switching issue is also prominent in the model. Additionally, the model is prone to getting caught in recursive reasoning loops, affecting the final output.

Credit-Read More

// Function to fetch the latest posts
function fetchLatestPosts() {
const feedUrl = ‘https://newskiosk.pro/feed/’; // Replace with your blog’s RSS feed URL
fetch(feedUrl)
.then(response => response.text())
.then(str => new window.DOMParser().parseFromString(str, “text/xml”))
.then(data => {
const items = Array.from(data.querySelectorAll(“item”));
const latestPostsContainer = document.getElementById(“latest-posts”);
latestPostsContainer.innerHTML = ”; // Clear previous posts

// Shuffle the items array
const shuffledItems = items.sort(() => Math.random() – 0.5);

// Select the first 5 items from the shuffled array
const selectedItems = shuffledItems.slice(0, 5);

// Loop through the selected items and display them
selectedItems.forEach(post => {
const link = post.querySelector(“link”).textContent;
const description = post.querySelector(“description”).textContent;

// Create a new post element
const postElement = document.createElement(“div”);
postElement.classList.add(“latest-post”);
postElement.innerHTML = `

${description} Read more

`;

// Append the new post element to the container
latestPostsContainer.appendChild(postElement);
});
})
.catch(error => console.error(‘Error fetching the latest posts:’, error));
}

// Call the function to fetch and display the latest posts
fetchLatestPosts();