<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd"
xmlns:podcast="https://podcastindex.org/namespace/1.0"
xmlns:rawvoice="https://blubrry.com/developer/rawvoice-rss/"
 xmlns:media="http://search.yahoo.com/mrss/" >

<channel>
	<title>Analytics Vidhya</title>
	<atom:link href="https://www.analyticsvidhya.com/feed/" rel="self" type="application/rss+xml" />
	<link>https://www.analyticsvidhya.com/</link>
	<description>Learn everything about Analytics</description>
	<lastBuildDate>Sat, 11 Jul 2026 19:19:17 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=6.8.3</generator>
	<atom:link rel="hub" href="https://pubsubhubbub.appspot.com/" />
	<itunes:summary>Learn everything about Analytics</itunes:summary>
	<itunes:author>Analytics Vidhya</itunes:author>
	<itunes:explicit>false</itunes:explicit>
	<itunes:image href="https://www.analyticsvidhya.com/wp-content/plugins/powerpress/itunes_default.jpg" />
	<itunes:owner>
		<itunes:name>Analytics Vidhya</itunes:name>
	</itunes:owner>
	<podcast:medium>podcast</podcast:medium>
	<itunes:subtitle>Learn everything about Analytics</itunes:subtitle>
	<image>
		<title>Analytics Vidhya</title>
		<url>https://www.analyticsvidhya.com/wp-content/plugins/powerpress/rss_default.jpg</url>
		<link>https://www.analyticsvidhya.com/blog-archive/</link>
	</image>
	<podcast:podping usesPodping="true" />
<atom:link rel="hub" href="https://pubsubhubbub.appspot.com"/><atom:link rel="hub" href="https://pubsubhubbub.superfeedr.com"/><atom:link rel="hub" href="https://flipboard.superfeedr.com"/><site xmlns="com-wordpress:feed-additions:1">180026056</site>	<item>
		<title>Handling Imbalanced Classification: What Works Better Than SMOTE</title>
		<link>https://www.analyticsvidhya.com/blog/2026/07/class-imbalance-ml/</link>
					<comments>https://www.analyticsvidhya.com/blog/2026/07/class-imbalance-ml/#respond</comments>
		
		<dc:creator><![CDATA[Vipin Vashisth]]></dc:creator>
		<pubDate>Sun, 12 Jul 2026 09:57:19 +0000</pubDate>
				<category><![CDATA[Advanced]]></category>
		<category><![CDATA[Beginner]]></category>
		<category><![CDATA[Machine Learning]]></category>
		<guid isPermaLink="false">https://www.analyticsvidhya.com/?p=256125</guid>

					<description><![CDATA[<p>Most real-world classification problems are imbalanced. Fraud, disease, churn, and defects are rare by nature. Standard classifiers chase accuracy, so they quietly ignore the very class you care about. For years, SMOTE was the reflex fix that everyone reached for first. But SMOTE often fails on the messy, high-dimensional data that production systems actually see. [&#8230;]</p>
<p>The post <a href="https://www.analyticsvidhya.com/blog/2026/07/class-imbalance-ml/">Handling Imbalanced Classification: What Works Better Than SMOTE</a> appeared first on <a href="https://www.analyticsvidhya.com">Analytics Vidhya</a>.</p>
]]></description>
		
					<wfw:commentRss>https://www.analyticsvidhya.com/blog/2026/07/class-imbalance-ml/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">256125</post-id>
	</item>
		<item>
		<title>RAG Evaluation Frameworks Compared: RAGAS vs TruLens vs DeepEval</title>
		<link>https://www.analyticsvidhya.com/blog/2026/07/rag-evaluation-frameworks/</link>
					<comments>https://www.analyticsvidhya.com/blog/2026/07/rag-evaluation-frameworks/#respond</comments>
		
		<dc:creator><![CDATA[Soumil Jain]]></dc:creator>
		<pubDate>Sat, 11 Jul 2026 18:16:00 +0000</pubDate>
				<category><![CDATA[Beginner]]></category>
		<category><![CDATA[LLMs]]></category>
		<category><![CDATA[RAG]]></category>
		<guid isPermaLink="false">https://www.analyticsvidhya.com/?p=256058</guid>

					<description><![CDATA[<p>LLMs are getting stronger every day, and building a RAG pipeline has never been easier. Knowing whether it actually works is not. Most teams ship a RAG system, see decent-looking answers, and call it done, until users hit hallucination, missing context, or irrelevant chunks. That&#8217;s where evaluation frameworks come in. RAGAS, TruLens, and DeepEval are [&#8230;]</p>
<p>The post <a href="https://www.analyticsvidhya.com/blog/2026/07/rag-evaluation-frameworks/">RAG Evaluation Frameworks Compared: RAGAS vs TruLens vs DeepEval</a> appeared first on <a href="https://www.analyticsvidhya.com">Analytics Vidhya</a>.</p>
]]></description>
		
					<wfw:commentRss>https://www.analyticsvidhya.com/blog/2026/07/rag-evaluation-frameworks/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">256058</post-id>
	</item>
		<item>
		<title>GPT-5.6 Is Here: Sol, Terra, and Luna</title>
		<link>https://www.analyticsvidhya.com/blog/2026/07/gpt-5-6-sol-terra-luna/</link>
					<comments>https://www.analyticsvidhya.com/blog/2026/07/gpt-5-6-sol-terra-luna/#respond</comments>
		
		<dc:creator><![CDATA[Vasu Deo Sankrityayan]]></dc:creator>
		<pubDate>Fri, 10 Jul 2026 04:19:50 +0000</pubDate>
				<category><![CDATA[ChatGPT]]></category>
		<category><![CDATA[LLMs]]></category>
		<guid isPermaLink="false">https://www.analyticsvidhya.com/?p=256190</guid>

					<description><![CDATA[<p>For twelve days, the best AI models on the planet existed and almost nobody could touch them. That ends now! GPT-5.6 Sol, Terra, and Luna go public today! The models are accessible by all users (no subscription required) This is the full breakdown of what&#8217;s on offer: three models, four prices, one precedent, and a [&#8230;]</p>
<p>The post <a href="https://www.analyticsvidhya.com/blog/2026/07/gpt-5-6-sol-terra-luna/">GPT-5.6 Is Here: Sol, Terra, and Luna</a> appeared first on <a href="https://www.analyticsvidhya.com">Analytics Vidhya</a>.</p>
]]></description>
		
					<wfw:commentRss>https://www.analyticsvidhya.com/blog/2026/07/gpt-5-6-sol-terra-luna/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">256190</post-id>
	</item>
		<item>
		<title>Loop Engineering for AI Agents: How /loop is Changing AI Workflows </title>
		<link>https://www.analyticsvidhya.com/blog/2026/07/loop-engineering-for-ai-agents/</link>
					<comments>https://www.analyticsvidhya.com/blog/2026/07/loop-engineering-for-ai-agents/#respond</comments>
		
		<dc:creator><![CDATA[Harsh Mishra]]></dc:creator>
		<pubDate>Thu, 09 Jul 2026 17:13:49 +0000</pubDate>
				<category><![CDATA[Artificial Intelligence]]></category>
		<category><![CDATA[Beginner]]></category>
		<category><![CDATA[LLMs]]></category>
		<guid isPermaLink="false">https://www.analyticsvidhya.com/?p=256095</guid>

					<description><![CDATA[<p>AI agents are moving from one-time assistants to persistent workers that can repeat tasks, monitor changes, run checks, update workflows, and return with results. Instead of prompting an LLM once and deciding every next step manually, teams can now use AI agents that keep working (on a Loop) until a goal or stop condition is [&#8230;]</p>
<p>The post <a href="https://www.analyticsvidhya.com/blog/2026/07/loop-engineering-for-ai-agents/">Loop Engineering for AI Agents: How /loop is Changing AI Workflows </a> appeared first on <a href="https://www.analyticsvidhya.com">Analytics Vidhya</a>.</p>
]]></description>
		
					<wfw:commentRss>https://www.analyticsvidhya.com/blog/2026/07/loop-engineering-for-ai-agents/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">256095</post-id>
	</item>
		<item>
		<title>DeepSeek DSpark: The Speculative Decoding Trick Behind 400% Faster LLM </title>
		<link>https://www.analyticsvidhya.com/blog/2026/07/deepseek-dspark-speculative-decoding/</link>
					<comments>https://www.analyticsvidhya.com/blog/2026/07/deepseek-dspark-speculative-decoding/#respond</comments>
		
		<dc:creator><![CDATA[Riya Bansal]]></dc:creator>
		<pubDate>Wed, 08 Jul 2026 18:26:00 +0000</pubDate>
				<category><![CDATA[Artificial Intelligence]]></category>
		<category><![CDATA[Beginner]]></category>
		<category><![CDATA[LLMs]]></category>
		<category><![CDATA[Research Paper]]></category>
		<guid isPermaLink="false">https://www.analyticsvidhya.com/?p=256047</guid>

					<description><![CDATA[<p>DeepSeek&#8217;s new DSpark module brings speculative decoding to DeepSeek-V4. It might look like a niche inference tweak, but in production it boosted per-user generation speed by 60 to 85 percent with no drop in model quality. What sets DSpark apart is that it tackles two longstanding problems at once, weak draft quality and the waste [&#8230;]</p>
<p>The post <a href="https://www.analyticsvidhya.com/blog/2026/07/deepseek-dspark-speculative-decoding/">DeepSeek DSpark: The Speculative Decoding Trick Behind 400% Faster LLM </a> appeared first on <a href="https://www.analyticsvidhya.com">Analytics Vidhya</a>.</p>
]]></description>
		
					<wfw:commentRss>https://www.analyticsvidhya.com/blog/2026/07/deepseek-dspark-speculative-decoding/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">256047</post-id>
	</item>
		<item>
		<title>OKF: Redefining Knowledge Bases for AI Agents</title>
		<link>https://www.analyticsvidhya.com/blog/2026/07/open-knowledge-format-okf/</link>
					<comments>https://www.analyticsvidhya.com/blog/2026/07/open-knowledge-format-okf/#respond</comments>
		
		<dc:creator><![CDATA[Shaik Hamzah]]></dc:creator>
		<pubDate>Tue, 07 Jul 2026 11:45:43 +0000</pubDate>
				<category><![CDATA[AI Agents]]></category>
		<category><![CDATA[Intermediate]]></category>
		<category><![CDATA[RAG]]></category>
		<guid isPermaLink="false">https://www.analyticsvidhya.com/?p=256066</guid>

					<description><![CDATA[<p>In June 2026, Google introduced the Open Knowledge Format (OKF), an open specification for how AI agents organise and exchange knowledge. An OKF bundle is just Markdown files, lightweight YAML metadata, and links between concepts, yet it challenges the assumption that every AI application needs embeddings and vector databases. Because the knowledge base is plain [&#8230;]</p>
<p>The post <a href="https://www.analyticsvidhya.com/blog/2026/07/open-knowledge-format-okf/">OKF: Redefining Knowledge Bases for AI Agents</a> appeared first on <a href="https://www.analyticsvidhya.com">Analytics Vidhya</a>.</p>
]]></description>
		
					<wfw:commentRss>https://www.analyticsvidhya.com/blog/2026/07/open-knowledge-format-okf/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">256066</post-id>
	</item>
		<item>
		<title>Modern VLMs Explained: How GPT-4o, Gemini, Claude Vision, and Qwen-VL Work </title>
		<link>https://www.analyticsvidhya.com/blog/2026/07/modern-vlms-explained/</link>
					<comments>https://www.analyticsvidhya.com/blog/2026/07/modern-vlms-explained/#respond</comments>
		
		<dc:creator><![CDATA[Janvi Kumari]]></dc:creator>
		<pubDate>Mon, 06 Jul 2026 05:14:11 +0000</pubDate>
				<category><![CDATA[Computer Vision]]></category>
		<category><![CDATA[Intermediate]]></category>
		<category><![CDATA[LLMs]]></category>
		<guid isPermaLink="false">https://www.analyticsvidhya.com/?p=256023</guid>

					<description><![CDATA[<p>Vision Language Models, or VLMs, are AI models that can understand both visual content and language. While earlier models like CLIP and BLIP connected images with text, modern VLMs can analyze images, read documents, interpret charts, answer visual questions, and support multimodal conversations. Models like GPT-4o, Gemini, Claude Vision, and Qwen-VL are making visual AI [&#8230;]</p>
<p>The post <a href="https://www.analyticsvidhya.com/blog/2026/07/modern-vlms-explained/">Modern VLMs Explained: How GPT-4o, Gemini, Claude Vision, and Qwen-VL Work </a> appeared first on <a href="https://www.analyticsvidhya.com">Analytics Vidhya</a>.</p>
]]></description>
		
					<wfw:commentRss>https://www.analyticsvidhya.com/blog/2026/07/modern-vlms-explained/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">256023</post-id>
	</item>
		<item>
		<title>YOLO26 Tutorial: Object Detection, Pose Estimation &#038; More</title>
		<link>https://www.analyticsvidhya.com/blog/2026/07/yolo26-tutorial/</link>
					<comments>https://www.analyticsvidhya.com/blog/2026/07/yolo26-tutorial/#respond</comments>
		
		<dc:creator><![CDATA[Mounish V]]></dc:creator>
		<pubDate>Sat, 04 Jul 2026 19:55:13 +0000</pubDate>
				<category><![CDATA[Beginner]]></category>
		<category><![CDATA[Computer Vision]]></category>
		<category><![CDATA[Machine Learning]]></category>
		<guid isPermaLink="false">https://www.analyticsvidhya.com/?p=255998</guid>

					<description><![CDATA[<p>Looking to model to implement pose estimation? I know something that can perform detection, instance segmentation, pose estimation and classification, all of that in real-time. Yes, I’m talking about the YOLO26 from ultralytics.&#160; It can aid security systems or can be fine-tuned to detect even smaller objects. Wondering how to get started? No worries, we’ll [&#8230;]</p>
<p>The post <a href="https://www.analyticsvidhya.com/blog/2026/07/yolo26-tutorial/">YOLO26 Tutorial: Object Detection, Pose Estimation &amp; More</a> appeared first on <a href="https://www.analyticsvidhya.com">Analytics Vidhya</a>.</p>
]]></description>
		
					<wfw:commentRss>https://www.analyticsvidhya.com/blog/2026/07/yolo26-tutorial/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">255998</post-id>
	</item>
		<item>
		<title>Large Action Models (LAMs) vs Agentic LLMs: What&#8217;s the Real Difference?</title>
		<link>https://www.analyticsvidhya.com/blog/2026/07/large-action-models-vs-agentic-llms/</link>
					<comments>https://www.analyticsvidhya.com/blog/2026/07/large-action-models-vs-agentic-llms/#respond</comments>
		
		<dc:creator><![CDATA[Sree Vamsi]]></dc:creator>
		<pubDate>Fri, 03 Jul 2026 18:28:00 +0000</pubDate>
				<category><![CDATA[AI Agents]]></category>
		<category><![CDATA[Artificial Intelligence]]></category>
		<category><![CDATA[Beginner]]></category>
		<category><![CDATA[LLMs]]></category>
		<guid isPermaLink="false">https://www.analyticsvidhya.com/?p=255945</guid>

					<description><![CDATA[<p>You tell your AI &#8220;Polish my email and send it.&#8221; Same sentence, three outcomes. The gap between Large Action Models (LAMs) and agentic LLMs is one of the most practically important distinctions in AI today, and also one of the least clearly explained. In this article, we cut through the confusion through a simple breakdown [&#8230;]</p>
<p>The post <a href="https://www.analyticsvidhya.com/blog/2026/07/large-action-models-vs-agentic-llms/">Large Action Models (LAMs) vs Agentic LLMs: What&#8217;s the Real Difference?</a> appeared first on <a href="https://www.analyticsvidhya.com">Analytics Vidhya</a>.</p>
]]></description>
		
					<wfw:commentRss>https://www.analyticsvidhya.com/blog/2026/07/large-action-models-vs-agentic-llms/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">255945</post-id>
	</item>
		<item>
		<title>Claude Sonnet 5: The Fable 5 at Home</title>
		<link>https://www.analyticsvidhya.com/blog/2026/07/claude-sonnet-5/</link>
					<comments>https://www.analyticsvidhya.com/blog/2026/07/claude-sonnet-5/#respond</comments>
		
		<dc:creator><![CDATA[Vasu Deo Sankrityayan]]></dc:creator>
		<pubDate>Tue, 30 Jun 2026 21:15:56 +0000</pubDate>
				<category><![CDATA[Artificial Intelligence]]></category>
		<category><![CDATA[LLMs]]></category>
		<guid isPermaLink="false">https://www.analyticsvidhya.com/?p=255975</guid>

					<description><![CDATA[<p>Anthropic has just released Claude Sonnet 5. Sonnet. Had to say it twice. It is the middle child of the Claude family, and the one most people will actually use. It is quick, capable, cheap to run, and free to use for all users without any subscription. In this article, we go over the latest [&#8230;]</p>
<p>The post <a href="https://www.analyticsvidhya.com/blog/2026/07/claude-sonnet-5/">Claude Sonnet 5: The Fable 5 at Home</a> appeared first on <a href="https://www.analyticsvidhya.com">Analytics Vidhya</a>.</p>
]]></description>
		
					<wfw:commentRss>https://www.analyticsvidhya.com/blog/2026/07/claude-sonnet-5/feed/</wfw:commentRss>
			<slash:comments>0</slash:comments>
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">255975</post-id>
	</item>
	</channel>
</rss>
