On July 10, Ant Lingbo released LingBot-VA 2.0, the industry's first realistic action model in a native world. According to the introduction, LingBot-VA 2.0 no longer follows the common “video generation model fine-tuning” route in the industry, but is pre-trained from scratch based on an autoregressive architecture, and is natively designed around the core requirements of robot interaction with the real environment, such as dynamic modeling, causal prediction, and real-time execution.

Disclaimer:Webull uses external vendor Google Translation Service for news translations where we endeavour to ensure these are correct, however, we recommend that you please double-check this information accordingly. Webull is not responsible for translation errors or issues.