mstdn.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A general-purpose Mastodon server with a 500 character limit. All languages are welcome.

Administered by:

Server stats:

15K
active users

#vlms

0 posts0 participants0 posts today
Hacker News<p>Benchmarking VLMs vs. Traditional OCR — <a href="https://getomni.ai/ocr-benchmark" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">getomni.ai/ocr-benchmark</span><span class="invisible"></span></a><br><a href="https://mastodon.social/tags/HackerNews" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>HackerNews</span></a> <a href="https://mastodon.social/tags/Benchmarking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Benchmarking</span></a> <a href="https://mastodon.social/tags/VLMs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLMs</span></a> <a href="https://mastodon.social/tags/TraditionalOCR" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TraditionalOCR</span></a> <a href="https://mastodon.social/tags/AItechnology" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AItechnology</span></a> <a href="https://mastodon.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MachineLearning</span></a> <a href="https://mastodon.social/tags/OCRbenchmark" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OCRbenchmark</span></a></p>
The New Stack<p>In <a href="https://hachyderm.io/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> agent development, you can add a persona to an agent using the system prompts available for <a href="https://hachyderm.io/tags/LLMs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLMs</span></a> and vision language models (<a href="https://hachyderm.io/tags/VLMs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLMs</span></a>).</p><p><a href="https://thenewstack.io/how-to-define-an-ai-agent-persona-by-tweaking-llm-prompts/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">thenewstack.io/how-to-define-a</span><span class="invisible">n-ai-agent-persona-by-tweaking-llm-prompts/</span></a></p>
Winbuzzer<p>ICYMI: A new study published on arXiv reveals fundamental issues in the visual reasoning abilities of leading AI vision-language models (VLMs) from OpenAI, Google, and Meta. <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="http://dlvr.it/TFrRmY" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">http://</span><span class="">dlvr.it/TFrRmY</span><span class="invisible"></span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/VLMs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLMs</span></a> <a href="https://mastodon.social/tags/OpenAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenAI</span></a></p>