101010.pl is one of the many independent Mastodon servers you can use to participate in the fediverse.
101010.pl czyli najstarszy polski serwer Mastodon. Posiadamy wpisy do 2048 znaków.

Server stats:

505
active users

#zeroshot

0 posts0 participants0 posts today
💧🌏 Greg Cocks<p>Segment Anything Model Can Not Segment Anything - Assessing AI Foundation Model’s Generalizability In Permafrost Mapping<br>--<br><a href="https://doi.org/10.3390/rs16050797" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">doi.org/10.3390/rs16050797</span><span class="invisible"></span></a> &lt;-- shared paper<br>--<br><a href="https://techhub.social/tags/GIS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GIS</span></a> <a href="https://techhub.social/tags/spatial" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>spatial</span></a> <a href="https://techhub.social/tags/mapping" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>mapping</span></a> <a href="https://techhub.social/tags/remotesensing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>remotesensing</span></a> <a href="https://techhub.social/tags/foundationmodel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>foundationmodel</span></a> <a href="https://techhub.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://techhub.social/tags/artificialintelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>artificialintelligence</span></a> <a href="https://techhub.social/tags/zeroshot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>zeroshot</span></a> <a href="https://techhub.social/tags/segmentation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>segmentation</span></a> <a href="https://techhub.social/tags/GeoAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GeoAI</span></a> <a href="https://techhub.social/tags/spatialanalysis" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>spatialanalysis</span></a> <a href="https://techhub.social/tags/LargeLanguageModel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LargeLanguageModel</span></a> <a href="https://techhub.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://techhub.social/tags/SAM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SAM</span></a> <a href="https://techhub.social/tags/performance" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>performance</span></a> <a href="https://techhub.social/tags/metrics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>metrics</span></a> <a href="https://techhub.social/tags/permafrost" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>permafrost</span></a> <a href="https://techhub.social/tags/visionmodel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>visionmodel</span></a> <a href="https://techhub.social/tags/icewedge" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>icewedge</span></a> <a href="https://techhub.social/tags/Arctic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Arctic</span></a> <a href="https://techhub.social/tags/warming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>warming</span></a> <a href="https://techhub.social/tags/climatechange" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>climatechange</span></a> <a href="https://techhub.social/tags/thawslumps" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>thawslumps</span></a> <a href="https://techhub.social/tags/landform" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>landform</span></a> <a href="https://techhub.social/tags/terrainmapping" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>terrainmapping</span></a> <a href="https://techhub.social/tags/EuroCrops" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EuroCrops</span></a> <a href="https://techhub.social/tags/agriculture" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>agriculture</span></a></p>
Pierre Monnin<p>Proud to announce our new paper, "Relevant Entity Selection: Knowledge Graph Bootstrapping via Zero-Shot Analogical Pruning" with Lucas Jarnac and Miguel Couceiro, accepted in <a href="https://sigmoid.social/tags/cikm2023" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cikm2023</span></a> </p><p><a href="https://sigmoid.social/tags/knowledgeGraph" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>knowledgeGraph</span></a> <a href="https://sigmoid.social/tags/machineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machineLearning</span></a> <a href="https://sigmoid.social/tags/graphEmbedding" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>graphEmbedding</span></a> <a href="https://sigmoid.social/tags/transferLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>transferLearning</span></a> <a href="https://sigmoid.social/tags/zeroShot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>zeroShot</span></a> <a href="https://sigmoid.social/tags/openScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>openScience</span></a></p>
Shiwali Mohan | शिवाली मोहन<p><span class="h-card"><a href="https://sigmoid.social/@Riedl" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>Riedl</span></a></span> </p><p>I have a <a href="https://sigmoid.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> that has 100% accuracy and <a href="https://sigmoid.social/tags/ZeroShot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ZeroShot</span></a> transfer on all blocks world problems. It is 'better than humans' who only have 80% accuracy. I call it the PDDLModel. With some prompt engineering (also called model writing), it can <a href="https://sigmoid.social/tags/zeroshot" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>zeroshot</span></a> transfer to other problems like tower-of-hanoi, 8-puzzle, eaters, and what not. It even fits on a raspberry pi. </p><p>We can only imagine what this new <a href="https://sigmoid.social/tags/AGI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AGI</span></a> would enable.</p><p><a href="https://github.com/gerryai/PDDL4J/blob/master/pddl/blockworld/blocksworld.pddl" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/gerryai/PDDL4J/blob</span><span class="invisible">/master/pddl/blockworld/blocksworld.pddl</span></a></p><p>Let's all play this game!!</p>