shakedown.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A community for live music fans with roots in the jam scene. Shakedown Social is run by a team of volunteers (led by @clifff and @sethadam1) and funded by donations.

Administered by:

Server stats:

245
active users

#foundationmodels

0 posts0 participants0 posts today
DurstewitzLab<p>Can time series (TS) <a href="https://mathstodon.xyz/tags/FoundationModels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>FoundationModels</span></a> (FM) like Chronos zero-shot generalize to unseen <a href="https://mathstodon.xyz/tags/DynamicalSystems" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DynamicalSystems</span></a> (DS)? <a href="https://mathstodon.xyz/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a></p><p>No, they cannot!</p><p>But *DynaMix* can, the first TS/DS foundation model based on principles of DS reconstruction, capturing the long-term evolution of out-of-domain DS: <a href="https://arxiv.org/pdf/2505.13192v1" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/pdf/2505.13192v1</span><span class="invisible"></span></a></p><p>Unlike TS foundation models, DynaMix exhibits <a href="https://mathstodon.xyz/tags/ZeroShotLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ZeroShotLearning</span></a> of long-term stats of unseen DS, incl. attractor geometry &amp; power spectrum, w/o *any* re-training, just from a context signal. <br>It does so with only 0.1% of the parameters of Chronos &amp; 10x faster inference times than the closest competitor.</p><p>It often even outperforms TS FMs on forecasting diverse empirical time series, like weather, traffic, or medical data, typically used to train TS FMs. <br>This is surprising, cos DynaMix’ training corpus consists *solely* of simulated limit cycles &amp; chaotic systems, no empirical data at all!</p><p>And no, it’s neither based on Transformers nor Mamba – it’s a new type of mixture-of-experts architecture based on the recently introduced AL-RNN (<a href="https://proceedings.neurips.cc/paper_files/paper/2024/file/40cf27290cc2bd98a428b567ba25075c-Paper-Conference.pdf" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">proceedings.neurips.cc/paper_f</span><span class="invisible">iles/paper/2024/file/40cf27290cc2bd98a428b567ba25075c-Paper-Conference.pdf</span></a>), specifically trained for DS reconstruction.</p><p>Remarkably, DynaMix not only generalizes zero-shot to novel DS, but it can even generalize to new initial conditions and regions of state space not covered by the in-context information.</p><p>We dive a bit into the reasons why current time series FMs not trained for DS reconstruction fail, and conclude that a DS perspective on time series forecasting &amp; models may help to advance the <a href="https://mathstodon.xyz/tags/TimeSeriesAnalysis" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TimeSeriesAnalysis</span></a> field.</p>
Toni Aittoniemi<p><span class="h-card" translate="no"><a href="https://techhub.social/@Techmeme" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>Techmeme</span></a></span> This is the danger of closed source</p><p>These are knowledge models, and they only output what they are fed with</p><p>And no, they won’t magically develop ’reasoning skills’ and be able to sift through propaganda. NOT when it’s part of the training</p><p>To think otherwise means you don’t know shit how they work</p><p>They obey statistics. Training data for <a href="https://mastodon.green/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a> <a href="https://mastodon.green/tags/foundationmodels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>foundationmodels</span></a> should be subject to public <a href="https://mastodon.green/tags/academic" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>academic</span></a> scrutiny. Otherwise the models are bound to fall for flooding attacks</p>
lkngrrr 🏳️‍🌈🏳️‍⚧️🏴‍☠️<p><a href="https://hachyderm.io/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GenerativeAI</span></a>, <a href="https://hachyderm.io/tags/FoundationModels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>FoundationModels</span></a>, <a href="https://hachyderm.io/tags/LLMs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLMs</span></a>, and all of that hokey nonsense shall not appear in my <a href="https://hachyderm.io/tags/robotics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>robotics</span></a> roadmaps as anything other than a neat research item until it can demonstrate a feasible path to <a href="https://hachyderm.io/tags/FunctionalSafety" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>FunctionalSafety</span></a> or mathematical completeness. </p><p>I lead <a href="https://hachyderm.io/tags/Product" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Product</span></a> on the largest mobile-<a href="https://hachyderm.io/tags/robotic" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>robotic</span></a> fleet known to humankind. I will not entrust decisions that could maim or kill to a pile of nondeterminate math prone to “hallucinations” or confabulation.</p><p><a href="https://hachyderm.io/tags/ProductManagement" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ProductManagement</span></a></p>
Erik Jonker<p>Prof. Yoshua Bengio warns in an op-ed for German newspaper Tagesspiegel: exempting foundation models from the AI Act would be both dangerous &amp; economically costly. It would make the AI Act "outdated from day one".<br><a href="https://background.tagesspiegel.de/digitalisierung/die-eu-droht-eine-einzigartige-chance-zu-verspielen" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">background.tagesspiegel.de/dig</span><span class="invisible">italisierung/die-eu-droht-eine-einzigartige-chance-zu-verspielen</span></a><br><a href="https://mastodon.social/tags/EU" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>EU</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/AIact" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIact</span></a> <a href="https://mastodon.social/tags/generativeAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>generativeAI</span></a> <a href="https://mastodon.social/tags/foundationmodels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>foundationmodels</span></a> <a href="https://mastodon.social/tags/Bengio" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Bengio</span></a></p>
IT News<p>University of Chicago researchers seek to “poison” AI art generators with Nightshade - Enlarge (credit: Getty Images) </p><p>On Friday, a team of researcher... - <a href="https://arstechnica.com/?p=1978501" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arstechnica.com/?p=1978501</span><span class="invisible"></span></a> <a href="https://schleuss.online/tags/largelanguagemodels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>largelanguagemodels</span></a> <a href="https://schleuss.online/tags/universityofchicago" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>universityofchicago</span></a> <a href="https://schleuss.online/tags/adversarialattacks" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>adversarialattacks</span></a> <a href="https://schleuss.online/tags/foundationmodels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>foundationmodels</span></a> <a href="https://schleuss.online/tags/machinelearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>machinelearning</span></a> <a href="https://schleuss.online/tags/aitrainingdata" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aitrainingdata</span></a> <a href="https://schleuss.online/tags/imagesynthesis" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>imagesynthesis</span></a> <a href="https://schleuss.online/tags/datapoisoning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>datapoisoning</span></a> <a href="https://schleuss.online/tags/nightshade" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nightshade</span></a> <a href="https://schleuss.online/tags/aiethics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aiethics</span></a> <a href="https://schleuss.online/tags/benzhao" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>benzhao</span></a> <a href="https://schleuss.online/tags/biz" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>biz</span></a>⁢ <a href="https://schleuss.online/tags/google" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>google</span></a> <a href="https://schleuss.online/tags/metaai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>metaai</span></a> <a href="https://schleuss.online/tags/openai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>openai</span></a> <a href="https://schleuss.online/tags/aiart" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>aiart</span></a> <a href="https://schleuss.online/tags/glaze" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>glaze</span></a> <a href="https://schleuss.online/tags/meta" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>meta</span></a> <a href="https://schleuss.online/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a></p>
Harald Sack<p>Hang in there, my fellow <a href="https://sigmoid.social/tags/knowledgegraph" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>knowledgegraph</span></a> researchers and practitioners, soon (in a few years) we will reach the "Slope of Enlightenment" ;-)<br>The new Gartner hype cycle for AI positions knowledge graphs right in the middle of the "Through of Disillusionment" ... while placing <a href="https://sigmoid.social/tags/GenerativeAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GenerativeAI</span></a> and <a href="https://sigmoid.social/tags/FoundationModels" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>FoundationModels</span></a> <a href="https://sigmoid.social/tags/LLMs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLMs</span></a> at the peak of the hype <br><a href="https://www.gartner.com/en/articles/what-s-new-in-artificial-intelligence-from-the-2023-gartner-hype-cycle#:~:text=The%202023%20Gartner%20Hype%20Cycle%E2%84%A2%20for%20Artificial%20Intelligence%20" rel="nofollow noopener noreferrer" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">gartner.com/en/articles/what-s</span><span class="invisible">-new-in-artificial-intelligence-from-the-2023-gartner-hype-cycle#:~:text=The%202023%20Gartner%20Hype%20Cycle%E2%84%A2%20for%20Artificial%20Intelligence%20</span></a>(AI,most%20credible%20cases%20for%20investment.<br><a href="https://sigmoid.social/tags/semanticweb" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>semanticweb</span></a> <a href="https://sigmoid.social/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a> <a href="https://sigmoid.social/tags/hypecycle" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>hypecycle</span></a> <a href="https://sigmoid.social/tags/artificialintelligence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>artificialintelligence</span></a></p>