WeChat team open-sources a 4B-parameter vision model with capabilities including counting, text recognition, and fine matting.
1 hours ago
Insight Beating AI News Flash: Tencent’s WeChat Vision team has open-sourced WeVisOne-VL, launching two versions: 2B and 4B. The model can complete a suite of tasks within a single framework, including object detection, counting, OCR text recognition, description-based object localization, image segmentation, and fine matting. For example, when asked to locate a person wearing red clothing in an image, it can mark their position and extract their silhouette. If the target is not present in the image, the model will return "None", reducing false positive detections. Traditional workflows typically require separate models for detection, Segment Anything Model (SAM) segmentation, and matting to operate sequentially. WeVisOne-VL is built on Qwen3-VL, encoding object coordinates into special tokens, then generating segmentation masks and transparent Alpha maps via a pixel decoder with only 9.6 million parameters to handle fine details like hair. The entire process eliminates the need for additional SAM calls. In tests released by Tencent, the 4B variant achieved an F1 score of 71.3 on Dense200 dense object detection, outperforming the strongest listed competitor’s 58.7; its PixMo-Count accuracy reached 89.6%, compared to 82.8% for baseline models. On the team’s self-built WeRef-Bench, it achieved a 96.4% false rejection rate for non-existent targets.
Gasoline and diesel prices set all-time records on U.S. Election Day.
7 minutes ago
The Philadelphia Semiconductor Index rose 4% intraday.
7 minutes ago
Speaker of the U.S. House of Representatives Johnson argues that polls are inaccurate.
7 minutes ago
He Yi: Binance has intercepted 57 suspected North Korea-related cyber threat incidents this year.
7 minutes ago
Mercado Bitcoin: Security incident results in $12.9 million in frozen assets, platform remains suspended.
7 minutes ago
Iran's Ministry of Foreign Affairs: No new progress has been made in the negotiations.
7 minutes ago
Hot feeds
A trader profits $448K by monitoring #Binance's new listings!
2024.12.13 17:37:29
Last week, funds have flowed into #Bitcoin, #Ethereum, and #Hyperliquid.
2024.12.16 14:48:36
A $PEPE whale that had been dormant for 600 days transferred all 2.1T $PEPE($52M) to a new address.
2024.12.14 10:35:27
When Elon Musk tweeted about Moltbook, the meme coin MOLT experienced a short-term 30% price surge, hitting a new all-time high of $114 million.
2026.01.31 18:37:29
A smart #AI coin trader made $17.6M on $GOAT, $ai16z, $Fartcoin,$arc.
2025.01.05 16:05:18
A sniper earned 2,277 $ETH ($8.3M) trading $SHIRO within 18 hours!
2024.12.03 23:09:08
MoreHot Articles

How did I turn $1,000 into $30,000 with smart money?
2024.12.09

10 promising AI Agent cryptos
2024.12.05

The 30-Year-Old Entrepreneur Behind Virtual, a Multi-Million Dollar AI Agent Society
2025.01.22

10 smart traders specializing in MEMEcoin trading on Solana
2024.12.09

A trader lost $73.9K trading memecoins in just 3 minutes — a lesson for us all!
2024.12.13

What is $SPORE? Let us take you through the on-chain records to show you how it works.
2024.12.25

