vision language models (VLM) - TechTalks https://bdtechtalks.com Technology solving problems... and creating new ones Mon, 24 Mar 2025 14:12:53 +0000 en-US hourly 1 https://i0.wp.com/bdtechtalks.com/wp-content/uploads/2018/02/cropped-TechTalks-logo.jpg?fit=32%2C32&ssl=1 vision language models (VLM) - TechTalks https://bdtechtalks.com 32 32 99082954 How Open-Sora 2.0 cuts the costs of AI video generation without sacrificing quality https://bdtechtalks.com/2025/03/24/open-sora-2/?utm_source=rss&utm_medium=rss&utm_campaign=open-sora-2 https://bdtechtalks.com/2025/03/24/open-sora-2/#respond Mon, 24 Mar 2025 14:11:14 +0000 https://bdtechtalks.com/?p=24158 Open-Sora 2.0 cuts the costs of creating a bleeding edge text-to-video AI model by using the right data, architecture, and training regime.

The post How Open-Sora 2.0 cuts the costs of AI video generation without sacrificing quality first appeared on TechTalks.

]]> https://bdtechtalks.com/2025/03/24/open-sora-2/feed/ 0 24158 Why vision-language models fail on simple visual tests https://bdtechtalks.com/2024/08/01/vlms-visual-test-failures/?utm_source=rss&utm_medium=rss&utm_campaign=vlms-visual-test-failures https://bdtechtalks.com/2024/08/01/vlms-visual-test-failures/#respond Thu, 01 Aug 2024 14:14:56 +0000 https://bdtechtalks.com/?p=22000 Vision-language models (VLMs) score high on competitive multi-modal benchmarks but fail on basic visual acuity tests, according to a new study.

The post Why vision-language models fail on simple visual tests first appeared on TechTalks.

]]> https://bdtechtalks.com/2024/08/01/vlms-visual-test-failures/feed/ 0 22000