CSBJ<p>🧬 Could AI deliver skin cancer diagnoses with the clarity and reasoning of a dermatologist?</p><p>🔗 A two-step concept-based approach for enhanced interpretability and trust in skin lesion diagnosis. DOI: <a href="https://doi.org/10.1016/j.csbj.2025.02.013" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">doi.org/10.1016/j.csbj.2025.02</span><span class="invisible">.013</span></a></p><p>📚 CSBJ Smart Hospital: <a href="https://www.csbj.org/smarthospital" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="">csbj.org/smarthospital</span><span class="invisible"></span></a></p><p><a href="https://mastodon.social/tags/AIinHealthcare" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIinHealthcare</span></a> <a href="https://mastodon.social/tags/ExplainableAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ExplainableAI</span></a> <a href="https://mastodon.social/tags/SkinCancer" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SkinCancer</span></a> <a href="https://mastodon.social/tags/VLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLM</span></a> <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> <a href="https://mastodon.social/tags/MedicalAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MedicalAI</span></a> <a href="https://mastodon.social/tags/TrustworthyAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TrustworthyAI</span></a> <a href="https://mastodon.social/tags/Dermatology" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Dermatology</span></a> <a href="https://mastodon.social/tags/XAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>XAI</span></a> <a href="https://mastodon.social/tags/PrecisionMedicine" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PrecisionMedicine</span></a></p>
Recent searches
No recent searches
Search options
Only available when logged in.
mastodon.world is one of the many independent Mastodon servers you can use to participate in the fediverse.
Generic Mastodon server for anyone to use.
Administered by:
Server stats:
11Kactive users
mastodon.world: About · Status · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.3.7
#vlm
3 posts · 3 participants · 0 posts today
Habr<p>[Перевод] Всё про инференс на Sophon NPU</p><p>В этой статье мы поговорим про ML на базе плат Sophon. Наверное это один из производителей которые набрали больше всего популярнсти в AI последнее время. Я расскажу как они соотносятся с другими платами на рынке (Jetson, RockChip, Hailo, TI, etc.). Расскажу как подготовить сети для работы на платформах, покажу ограничения (что пока нельзя сделать, ограничения по скорости, и.т.д.).</p><p><a href="https://habr.com/ru/companies/recognitor/articles/898152/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">habr.com/ru/companies/recognit</span><span class="invisible">or/articles/898152/</span></a></p><p><a href="https://zhub.link/tags/Sophon" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Sophon</span></a> <a href="https://zhub.link/tags/NPU" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NPU</span></a> <a href="https://zhub.link/tags/Jetson" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Jetson</span></a> <a href="https://zhub.link/tags/RockChip" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RockChip</span></a> <a href="https://zhub.link/tags/ML" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ML</span></a> <a href="https://zhub.link/tags/Edge_Inference" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Edge_Inference</span></a> <a href="https://zhub.link/tags/Computer_Vision" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Computer_Vision</span></a> <a href="https://zhub.link/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> <a href="https://zhub.link/tags/VLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLM</span></a> <a href="https://zhub.link/tags/Qwen" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Qwen</span></a></p>
LLMs[Перевод] Всё про инференс на Sophon NPU В этой статье мы п...<br><br><a href="https://habr.com/ru/companies/recognitor/articles/898152/?utm_source=habrahabr&utm_medium=rss&utm_campaign=898152" rel="nofollow noopener noreferrer" target="_blank">https://habr.com/ru/companies/recognitor/articles/898152/?utm_source=habrahabr&utm_medium=rss&utm_campaign=898152</a><br><br><a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/Sophon" target="_blank">#Sophon</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/NPU" target="_blank">#NPU</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/Jetson" target="_blank">#Jetson</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/RockChip" target="_blank">#RockChip</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/ML" target="_blank">#ML</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/Edge" target="_blank">#Edge</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/Inference" target="_blank">#Inference</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/Computer" target="_blank">#Computer</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/Vision" target="_blank">#Vision</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/LLM" target="_blank">#LLM</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/VLM" target="_blank">#VLM</a><br><br><a href="https://awakari.com/pub-msg.html?id=G8WDLv2oXEJSxhOKlSQu1GSW384" rel="nofollow noopener noreferrer" target="_blank">Event Attributes</a>
Hacker News<p>SmolDocling: An ultra-compact VLM for end-to-end multi-modal document conversion</p><p><a href="https://arxiv.org/abs/2503.11576" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2503.11576</span><span class="invisible"></span></a></p><p><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/SmolDocling" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SmolDocling</span></a> <a href="https://mastodon.social/tags/VLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLM</span></a> <a href="https://mastodon.social/tags/documentconversion" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>documentconversion</span></a> <a href="https://mastodon.social/tags/multimodal" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>multimodal</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a></p>
GripNews<p>🌘 VLM執行食譜展示<br>➤ GitHub VLM執行食譜的功能介紹<br>✤ <a href="https://github.com/vlm-run/vlmrun-cookbook/blob/main/notebooks/01_schema_showcase.ipynb" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/vlm-run/vlmrun-cook</span><span class="invisible">book/blob/main/notebooks/01_schema_showcase.ipynb</span></a><br>本文介紹了GitHub上VLM執行食譜的相應notebook，涵蓋多個功能，並提供各種自動化工作流程的框架。文中提到GitHub的安全性、開發工具及社區合作等主題，強調開源開發的重要性。<br>+ 這篇文章真是幫助我瞭解VLM的各種功能，非常有用！<br>+ 我非常喜歡開源開發的理念，希望能看到更多相關的資源和工具介紹。<br><a href="https://mastodon.social/tags/GitHub" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GitHub</span></a> <a href="https://mastodon.social/tags/VLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLM</span></a> <a href="https://mastodon.social/tags/%E8%BB%9F%E9%AB%94%E9%96%8B%E7%99%BC" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>軟體開發</span></a></p>
💧🌏 Greg Cocks<p>Satellite Data Study Pinpoints Areas Sinking And Rising Along California Coast<br>--<br><a href="https://phys.org/news/2025-02-satellite-areas-california-coast.html" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">phys.org/news/2025-02-satellit</span><span class="invisible">e-areas-california-coast.html</span></a> <-- shared technical article<br>--<br><a href="https://dx.doi.org/10.1126/sciadv.ads8163" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">dx.doi.org/10.1126/sciadv.ads8</span><span class="invisible">163</span></a> <-- shared paper<br>--<br><a href="https://techhub.social/tags/GIS" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GIS</span></a> <a href="https://techhub.social/tags/spatial" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>spatial</span></a> <a href="https://techhub.social/tags/mapping" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>mapping</span></a> <a href="https://techhub.social/tags/sealevel" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>sealevel</span></a> <a href="https://techhub.social/tags/sealevelrise" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>sealevelrise</span></a> <a href="https://techhub.social/tags/subsidence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>subsidence</span></a> <a href="https://techhub.social/tags/model" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>model</span></a> <a href="https://techhub.social/tags/modeling" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>modeling</span></a> <a href="https://techhub.social/tags/SLR" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SLR</span></a> <a href="https://techhub.social/tags/coast" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>coast</span></a> <a href="https://techhub.social/tags/coastline" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>coastline</span></a> <a href="https://techhub.social/tags/verticallandmotion" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>verticallandmotion</span></a> <a href="https://techhub.social/tags/VLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLM</span></a> <a href="https://techhub.social/tags/California" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>California</span></a> <a href="https://techhub.social/tags/climatechange" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>climatechange</span></a> <a href="https://techhub.social/tags/planning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>planning</span></a> <a href="https://techhub.social/tags/policy" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>policy</span></a> <a href="https://techhub.social/tags/remotesensing" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>remotesensing</span></a> <a href="https://techhub.social/tags/groundwater" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>groundwater</span></a> <a href="https://techhub.social/tags/pumping" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pumping</span></a> <a href="https://techhub.social/tags/risk" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>risk</span></a> <a href="https://techhub.social/tags/hazard" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>hazard</span></a> <a href="https://techhub.social/tags/infrastructure" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>infrastructure</span></a> <a href="https://techhub.social/tags/damage" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>damage</span></a> <a href="https://techhub.social/tags/wastewater" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>wastewater</span></a> <a href="https://techhub.social/tags/injection" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>injection</span></a> <a href="https://techhub.social/tags/tidegauge" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tidegauge</span></a> <a href="https://techhub.social/tags/dynamic" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>dynamic</span></a> <a href="https://techhub.social/tags/spatialanalysis" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>spatialanalysis</span></a> <a href="https://techhub.social/tags/spatiotemporal" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>spatiotemporal</span></a> <a href="https://techhub.social/tags/numericmodeling" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>numericmodeling</span></a> <a href="https://techhub.social/tags/uplift" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>uplift</span></a> <a href="https://techhub.social/tags/projections" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>projections</span></a> <a href="https://techhub.social/tags/flood" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>flood</span></a> <a href="https://techhub.social/tags/flooding" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>flooding</span></a> <a href="https://techhub.social/tags/mitigation" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>mitigation</span></a> <a href="https://techhub.social/tags/satellite" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>satellite</span></a> <a href="https://techhub.social/tags/ocean" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ocean</span></a> <a href="https://techhub.social/tags/marine" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>marine</span></a><br><span class="h-card" translate="no"><a href="https://techhub.social/@nasa" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>nasa</span></a></span></p>
Alex<p><span class="h-card" translate="no"><a href="https://toot.wales/@gilesgoat" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>gilesgoat</span></a></span> <span class="h-card" translate="no"><a href="https://toot.wales/@llamasoft_ox" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>llamasoft_ox</span></a></span> is the <a href="https://mastodon.org.uk/tags/VLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLM</span></a> a library you use between multiple games? How much relation does it have to the original Trip-a-Tron I played with on my <a href="https://mastodon.org.uk/tags/atarist" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>atarist</span></a>?</p>
Estelle FLAUJATPensée du 41ème jour, 10 février <br>
<br>
Une goutte d'eau<br>
<br>
Ce monde,<br>
À quoi le comparer ?<br>
À la goutte qui tombe<br>
Du bec de l'oiseau d'eau<br>
Et réfléchit le clair de lune. ~ Dōgen Zenji<br>
<br>
Fugacité du monde. Fugacité de la vie de cet être conscient qui perçoit le monde. L'existence en ce monde comme la goutte d'eau qui vient tomber du bec d'un héron et qui s'en va rejoindre l'étang, le conglomérat de toutes les gouttes d'eau. Et dans cette chute qui ne dure que quelques instants, le reflet de la lune habite la transparence de la goutte d'eau. <br>
<br>
Notre existence peut sembler infinitésimale tant dans l'espace et dans le temps. Pour autant, elle peut refléter la lumière de l'Éveil. <br>
<br>
Ne plus être cette seule goutte prise dans les turbulences de la chute, mais être l'étang et l'oiseau d'eau qui contemple le grand calme de l'étang dans l'aube brumeuse.<br>
.<br>
.<br>
.<br>
[D'après Bai Wenshu]<br>
.<br>
<a href="https://pixelfed.social/discover/tags/pensée?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#pensée</a> <a href="https://pixelfed.social/discover/tags/penséedujour?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#penséedujour</a> <a href="https://pixelfed.social/discover/tags/penséepositive?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#penséepositive</a> <a href="https://pixelfed.social/discover/tags/bienveillance?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#bienveillance</a> <a href="https://pixelfed.social/discover/tags/inspiration?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#inspiration</a> <a href="https://pixelfed.social/discover/tags/optimisme?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#optimisme</a> <a href="https://pixelfed.social/discover/tags/citation?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#citation</a> <a href="https://pixelfed.social/discover/tags/philosophie?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#philosophie</a> <a href="https://pixelfed.social/discover/tags/calme?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#calme</a> <a href="https://pixelfed.social/discover/tags/contemplation?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#contemplation</a> <a href="https://pixelfed.social/discover/tags/immobilite?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#immobilite</a> <a href="https://pixelfed.social/discover/tags/zazen?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#zazen</a> <a href="https://pixelfed.social/discover/tags/meditation?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#meditation</a> <a href="https://pixelfed.social/discover/tags/Montpellier?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#Montpellier</a> <a href="https://pixelfed.social/discover/tags/VLM?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#VLM</a> <a href="https://pixelfed.social/discover/tags/photo?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#photo</a> <a href="https://pixelfed.social/discover/tags/art?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#art</a> <a href="https://pixelfed.social/discover/tags/philosophy?src=hash" class="u-url hashtag" rel="nofollow noopener noreferrer" target="_blank">#philosophy</a>
John Leonard<p>Hugging Face has introduced two new models in its SmolVLM series, which it claims are the smallest Vision Language Models (VLMs) to date.</p><p><a href="https://www.computing.co.uk/news/2025/ai/hugging-face-claims-world-s-smallest-vision-language-models" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">computing.co.uk/news/2025/ai/h</span><span class="invisible">ugging-face-claims-world-s-smallest-vision-language-models</span></a></p><p><a href="https://mastodon.social/tags/huggingface" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>huggingface</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/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llm</span></a> <a href="https://mastodon.social/tags/technews" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>technews</span></a> <a href="https://mastodon.social/tags/opensource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>opensource</span></a> <a href="https://mastodon.social/tags/vlm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>vlm</span></a></p>
Habr<p>Обработка каталога и товаров на LLM</p><p>Существует классическая проблема на любой электронной торговой площадке, связанная с тем, как категоризировать и понять описания товаров. Особенно она усугубляется тем, что пользователи создают запутанные описания даже для самых простых продуктов. Например, обычная синяя футболка может быть описана как небесно-голубая или даже тёмно-сине-аквамариновая. Что могут предложить современные LLM и VLM для решения проблемы?</p><p><a href="https://habr.com/ru/companies/raft/articles/874966/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">habr.com/ru/companies/raft/art</span><span class="invisible">icles/874966/</span></a></p><p><a href="https://zhub.link/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llm</span></a> <a href="https://zhub.link/tags/vlm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>vlm</span></a> <a href="https://zhub.link/tags/%D0%BC%D0%B0%D1%80%D0%BA%D0%B5%D1%82%D0%BF%D0%BB%D0%B5%D0%B9%D1%81" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>маркетплейс</span></a> <a href="https://zhub.link/tags/matching" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>matching</span></a></p>
Habr<p>Обработка и сравнение товаров маркетплейсов на LLM</p><p>Существует классическая проблема на любой электронной торговой площадке, связанная с тем, как категоризировать и понять описания товаров. Особенно она усугубляется тем, что пользователи создают запутанные описания даже для самых простых продуктов. Например, обычная синяя футболка может быть описана как небесно-голубая или даже тёмно-сине-аквамариновая. Что могут предложить современные LLM и VLM для решения проблеммы?</p><p><a href="https://habr.com/ru/companies/raft/articles/874602/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">habr.com/ru/companies/raft/art</span><span class="invisible">icles/874602/</span></a></p><p><a href="https://zhub.link/tags/%D0%BC%D0%B0%D1%80%D0%BA%D0%B5%D1%82%D0%BF%D0%BB%D0%B5%D0%B9%D1%81" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>маркетплейс</span></a> <a href="https://zhub.link/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llm</span></a> <a href="https://zhub.link/tags/vlm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>vlm</span></a> <a href="https://zhub.link/tags/%D0%B0%D0%BD%D0%B0%D0%BB%D0%B8%D0%B7_%D1%82%D0%BE%D0%B2%D0%B0%D1%80%D0%BE%D0%B2" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>анализ_товаров</span></a> <a href="https://zhub.link/tags/matching" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>matching</span></a></p>
💧🌏 Greg Cocks<p>Projections Of Multiple Climate-Related Coastal Hazards For The US Southeast Atlantic<br>--<br><a href="https://doi.org/10.1038/s41558-024-02180-2" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">doi.org/10.1038/s41558-024-021</span><span class="invisible">80-2</span></a> <-- shared paper<br>--<br><a href="https://techhub.social/tags/GIS" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GIS</span></a> <a href="https://techhub.social/tags/spatial" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>spatial</span></a> <a href="https://techhub.social/tags/mapping" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>mapping</span></a> <a href="https://techhub.social/tags/coast" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>coast</span></a> <a href="https://techhub.social/tags/coastal" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>coastal</span></a> <a href="https://techhub.social/tags/water" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>water</span></a> <a href="https://techhub.social/tags/hydrology" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>hydrology</span></a> <a href="https://techhub.social/tags/risk" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>risk</span></a> <a href="https://techhub.social/tags/hazard" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>hazard</span></a> <a href="https://techhub.social/tags/VLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLM</span></a> <a href="https://techhub.social/tags/VerticalLandMotion" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VerticalLandMotion</span></a> <a href="https://techhub.social/tags/SeaLevel" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SeaLevel</span></a> <a href="https://techhub.social/tags/SealLevelRise" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SealLevelRise</span></a> <a href="https://techhub.social/tags/SLR" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SLR</span></a> <a href="https://techhub.social/tags/climatechange" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>climatechange</span></a> <a href="https://techhub.social/tags/extremeweather" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>extremeweather</span></a> <a href="https://techhub.social/tags/US" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>US</span></a> <a href="https://techhub.social/tags/USA" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>USA</span></a> <a href="https://techhub.social/tags/SoutheastAtlantic" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SoutheastAtlantic</span></a> <a href="https://techhub.social/tags/Atlantic" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Atlantic</span></a> <a href="https://techhub.social/tags/storm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>storm</span></a> <a href="https://techhub.social/tags/stormsurge" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>stormsurge</span></a> <a href="https://techhub.social/tags/erosion" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>erosion</span></a> <a href="https://techhub.social/tags/groundwater" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>groundwater</span></a> <a href="https://techhub.social/tags/flood" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>flood</span></a> <a href="https://techhub.social/tags/flooding" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>flooding</span></a> <a href="https://techhub.social/tags/subsidence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>subsidence</span></a> <a href="https://techhub.social/tags/society" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>society</span></a> <a href="https://techhub.social/tags/societal" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>societal</span></a> <a href="https://techhub.social/tags/cost" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>cost</span></a> <a href="https://techhub.social/tags/infrastructure" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>infrastructure</span></a> <a href="https://techhub.social/tags/economics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>economics</span></a> <a href="https://techhub.social/tags/saltwater" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>saltwater</span></a> <a href="https://techhub.social/tags/property" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>property</span></a> <a href="https://techhub.social/tags/value" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>value</span></a> <a href="https://techhub.social/tags/beaches" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>beaches</span></a> <a href="https://techhub.social/tags/saltwaterintrusion" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>saltwaterintrusion</span></a></p>
michabbb<p>Breakthrough in Visual Language Models and Reasoning 🧠</p><p>🔍 <a href="https://social.vivaldi.net/tags/LLaVAo1" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLaVAo1</span></a> pioneers systematic visual reasoning capabilities:<br>• First <a href="https://social.vivaldi.net/tags/VLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLM</span></a> to implement spontaneous step-by-step analysis like <a href="https://social.vivaldi.net/tags/GPT4" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GPT4</span></a><br>• New 11B model surpasses <a href="https://social.vivaldi.net/tags/Gemini15pro" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Gemini15pro</span></a> & <a href="https://social.vivaldi.net/tags/Llama32" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Llama32</span></a> performance<br>• Excels on 6 multimodal benchmark tests<br>• Breaks down complex problems into structured analysis stages</p><p>🎯 Key Features:<br>• Problem outline creation<br>• Image information interpretation<br>• Sequential reasoning process<br>• Evidence-based conclusions<br>• Handles science & reasoning challenges</p><p>💡 Technical Specs:<br>• Based on <a href="https://social.vivaldi.net/tags/opensource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>opensource</span></a> architecture<br>• Pretrained weights available on <a href="https://social.vivaldi.net/tags/HuggingFace" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>HuggingFace</span></a><br>• 11B parameter model size<br>• Supports multiple reasoning domains</p><p>📚 Paper available: <a href="https://arxiv.org/abs/2411.10440" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2411.10440</span><span class="invisible"></span></a><br>🔗 Project repository: <a href="https://github.com/PKU-YuanGroup/LLaVA-o1" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/PKU-YuanGroup/LLaVA</span><span class="invisible">-o1</span></a></p>
Dr James Ravenscroft<p>Earlier this year I wrote about my handwriting <a href="https://fosstodon.org/tags/OCR" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OCR</span></a> workflow. I wanted to reduce the friction in this flow so I spent some time building a telegram bot that uses <a href="https://fosstodon.org/tags/VLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLM</span></a> models to OCR my hand writing. Introducing AnnoMemo which is open source and easyish to self-host. Currently it uses remote models but I'm planning to integrate Qwen2-VL 2B which a) understands my handwriting perfectly and b) runs on my desktop GPU. Considering providing a managed service too <a href="https://brainsteam.co.uk/2024/11/3/03-annomemo-telegram-bot/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">brainsteam.co.uk/2024/11/3/03-</span><span class="invisible">annomemo-telegram-bot/</span></a></p>
mancavgeek<p></p><p>Photo of the Day 1st November 2024.</p>PH-BDT, Boeing 737-406, KLM, being pushed back from Gate 24 at Manchester Airport, some time in the 1990s.<p> </p><p>On This Day 1st November 1993.</p>F-GIJT, Airbus A300B4-103, Air Inter, under tow at Paris Orly, 1st November 1993.<p> </p><p>On This Day 1st November 1994.</p>OO-VLN, Fokker F50, VLM, taxiing out to Runway 27 at London City Airport, 1st November 1994.<p><a href="https://mancavgeek.co.uk/2024/11/01/photo-of-the-day-1st-november-2024/" class="" rel="nofollow noopener noreferrer" target="_blank">https://mancavgeek.co.uk/2024/11/01/photo-of-the-day-1st-november-2024/</a></p><p><a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/a300/" target="_blank">#a300</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/airbus/" target="_blank">#airbus</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/airinter/" target="_blank">#AirInter</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/avgeek/" target="_blank">#avgeek</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/aviation/" target="_blank">#aviation</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/b737/" target="_blank">#b737</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/boeing/" target="_blank">#boeing</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/city/" target="_blank">#city</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/egcc/" target="_blank">#egcc</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/eglc/" target="_blank">#eglc</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/f50/" target="_blank">#f50</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/fokker/" target="_blank">#fokker</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/klm/" target="_blank">#KLM</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/lcy/" target="_blank">#lcy</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/lfpo/" target="_blank">#lfpo</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/london/" target="_blank">#london</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/man/" target="_blank">#man</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/manchester/" target="_blank">#manchester</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/onthisday/" target="_blank">#OnThisDay</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/orly/" target="_blank">#orly</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/ory/" target="_blank">#ory</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/paris/" target="_blank">#paris</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/photography/" target="_blank">#photography</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/planespotting/" target="_blank">#planespotting</a> <a rel="nofollow noopener noreferrer" class="hashtag u-tag u-category" href="https://mancavgeek.co.uk/tag/vlm/" target="_blank">#VLM</a></p>
Habr<p>VLM — арт эксперты</p><p>Всем привет, меня зовут Арсений, я DS в компании Raft, и сегодня я расскажу вам про VLM. Большие языковые модели уже стали частью нашей жизни и мы применяем, чтобы упростить современную рутину, а так же используем их для решения бизнес задач. Недавно вышло новое поколение vision transformer моделей, которые заметно упростили анализ изображений, из какой бы сферы эти изображения не были. Особенно заметным был сентябрьский релиз Llama-3.2-11b, и не только потому что это первая vision модель от Llama, сколько потому, что с ней вместе вышло целое семейство моделей, включая маленькие на 1B и 3B параметров. А как вы знаете, меньше, значит юзабельнее.</p><p><a href="https://habr.com/ru/articles/854864/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">habr.com/ru/articles/854864/</span><span class="invisible"></span></a></p><p><a href="https://zhub.link/tags/transformers" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>transformers</span></a> <a href="https://zhub.link/tags/VLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLM</span></a> <a href="https://zhub.link/tags/Vision_Transformer" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Vision_Transformer</span></a> <a href="https://zhub.link/tags/llama_32" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llama_32</span></a> <a href="https://zhub.link/tags/llava" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llava</span></a> <a href="https://zhub.link/tags/qwen2vl" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>qwen2vl</span></a> <a href="https://zhub.link/tags/art" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>art</span></a> <a href="https://zhub.link/tags/art_history" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>art_history</span></a> <a href="https://zhub.link/tags/%D0%B8%D1%81%D0%BA%D1%83%D1%81%D1%81%D1%82%D0%B2%D0%B5%D0%BD%D0%BD%D1%8B%D0%B9_%D0%B8%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>искусственный_интеллект</span></a></p>
Winbuzzer<p>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/TFpXr8" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">http://</span><span class="">dlvr.it/TFpXr8</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/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://mastodon.social/tags/VLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VLM</span></a></p>
Robotics papers<p>SKT: Integrating State-Aware Keypoint Trajectories with Vision-Language Models for Robotic Garment Manipulation</p><p>Authors: Xin Li, Siyuan Huang, Qiaojun Yu, Zhengkai Jiang, Ce Hao, Yimeng Zhu, Hongsheng Li, Peng Gao, Cewu Lu</p><p>pre-print -> <a href="https://arxiv.org/abs/2409.18082" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2409.18082</span><span class="invisible"></span></a><br>project website -> <a href="https://sites.google.com/view/keypoint-garment/home" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">sites.google.com/view/keypoint</span><span class="invisible">-garment/home</span></a></p><p><a href="https://mastodon.social/tags/robotics" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>robotics</span></a> <a href="https://mastodon.social/tags/deformable_manipulation" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>deformable_manipulation</span></a> <a href="https://mastodon.social/tags/garment_manipulation" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>garment_manipulation</span></a> <a href="https://mastodon.social/tags/vlm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>vlm</span></a></p>
Habr<p>VLM в Нейро: как мы создавали мультимодальную нейросеть для поиска по картинкам</p><p>Сегодня у Поиска большое обновление. Например, ответы Нейро теперь будут появляться сразу в поисковых результатах — для тех запросов, где это полезно и экономит время. Но в рамках этой статьи нас интересует другая часть обновления: Нейро поможет найти ответы в Поиске по картинкам и в Умной камере — с помощью новой мультимодальной модели Яндекса. Пользователь может не только узнать, что изображено на картинке, но и задать вопрос по каждой её детали. Например, гуляя по музею, можно сфотографировать натюрморт голландского живописца и спросить, что символизирует тот или иной предмет на картине. Меня зовут Роман Исаченко, я работаю в команде компьютерного зрения Яндекса. В этой статье я расскажу, что такое визуально‑текстовые мультимодальные модели (Visual Language Models или VLM), как у нас в Яндексе организован процесс их обучения и какая у них архитектура. Вы узнаете, как Нейро работал с картинками и текстами раньше, и что изменилось с появлением VLM.</p><p><a href="https://habr.com/ru/companies/yandex/articles/847706/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">habr.com/ru/companies/yandex/a</span><span class="invisible">rticles/847706/</span></a></p><p><a href="https://zhub.link/tags/%D1%8F%D0%BD%D0%B4%D0%B5%D0%BA%D1%81" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>яндекс</span></a> <a href="https://zhub.link/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llm</span></a> <a href="https://zhub.link/tags/vlm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>vlm</span></a> <a href="https://zhub.link/tags/computer_vision" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>computer_vision</span></a> <a href="https://zhub.link/tags/%D0%BF%D0%BE%D0%B8%D1%81%D0%BA%D0%BE%D0%B2%D1%8B%D0%B5_%D1%81%D0%B8%D1%81%D1%82%D0%B5%D0%BC%D1%8B" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>поисковые_системы</span></a> <a href="https://zhub.link/tags/%D0%BD%D0%B5%D0%B9%D1%80%D0%BE%D1%81%D0%B5%D1%82%D0%B8" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>нейросети</span></a></p>
SearchEngineVLM в Нейро: как мы создавали мультимодальную нейросет...<br><br><a href="https://habr.com/ru/companies/yandex/articles/847706/?utm_source=habrahabr&utm_medium=rss&utm_campaign=847706" rel="nofollow noopener noreferrer" target="_blank">https://habr.com/ru/companies/yandex/articles/847706/?utm_source=habrahabr&utm_medium=rss&utm_campaign=847706</a><br><br><a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/яндекс" target="_blank">#яндекс</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/llm" target="_blank">#llm</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/vlm" target="_blank">#vlm</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/computer" target="_blank">#computer</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/vision" target="_blank">#vision</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/поисковые" target="_blank">#поисковые</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/системы" target="_blank">#системы</a> <a rel="nofollow noopener noreferrer" class="mention hashtag" href="https://mastodon.social/tags/нейросети" target="_blank">#нейросети</a><br><br><a href="https://awakari.com/pub-msg.html?id=2mvA2U7SKoOUdVoYjuTTVrfd3Yd" rel="nofollow noopener noreferrer" target="_blank">Event Attributes</a>
ExploreLive feeds
Mastodon is the best way to keep up with what's happening.
Follow anyone across the fediverse and see it all in chronological order. No algorithms, ads, or clickbait in sight.
Create accountLoginDrag & drop to upload