<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Thao Vu on Medium]]></title>
        <description><![CDATA[Stories by Thao Vu on Medium]]></description>
        <link>https://medium.com/@vuphuongthao9611?source=rss-a836aac352ca------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*LBWa57M8w5DbNZouS7sNhg@2x.jpeg</url>
            <title>Stories by Thao Vu on Medium</title>
            <link>https://medium.com/@vuphuongthao9611?source=rss-a836aac352ca------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Mon, 16 Nov 2026 03:16:50 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@vuphuongthao9611/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Transformers: From NLP to Computer Vision]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/transformers-from-nlp-to-computer-vision-4f237386610c?source=rss-a836aac352ca------2"><img src="https://cdn-images-1.medium.com/max/2600/0*A0f6Wit1G08hfFqz" width="3898"></a></p><p class="medium-feed-snippet">How Transformer architecture has been adapted to computer vision tasks</p><p class="medium-feed-link"><a href="https://medium.com/data-science/transformers-from-nlp-to-computer-vision-4f237386610c?source=rss-a836aac352ca------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/transformers-from-nlp-to-computer-vision-4f237386610c?source=rss-a836aac352ca------2</link>
            <guid isPermaLink="false">https://medium.com/p/4f237386610c</guid>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[nlp]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[computer-vision]]></category>
            <dc:creator><![CDATA[Thao Vu]]></dc:creator>
            <pubDate>Sun, 05 May 2024 17:05:49 GMT</pubDate>
            <atom:updated>2024-05-05T17:05:49.667Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Optimizing Multi-task Learning Models in Practice]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/optimizing-multi-task-learning-models-in-practice-bde4f18f0bd8?source=rss-a836aac352ca------2"><img src="https://cdn-images-1.medium.com/max/2600/0*9hHGPyHbbRvLDzta" width="5581"></a></p><p class="medium-feed-snippet">What is multi-task learning models, and how to optimize them</p><p class="medium-feed-link"><a href="https://medium.com/data-science/optimizing-multi-task-learning-models-in-practice-bde4f18f0bd8?source=rss-a836aac352ca------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/optimizing-multi-task-learning-models-in-practice-bde4f18f0bd8?source=rss-a836aac352ca------2</link>
            <guid isPermaLink="false">https://medium.com/p/bde4f18f0bd8</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[machine-learning]]></category>
            <dc:creator><![CDATA[Thao Vu]]></dc:creator>
            <pubDate>Fri, 29 Mar 2024 15:42:03 GMT</pubDate>
            <atom:updated>2024-04-10T07:22:18.431Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Correct Sampling Bias for Recommender Systems]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/correct-sampling-bias-for-recommender-systems-d2f6d9fdddec?source=rss-a836aac352ca------2"><img src="https://cdn-images-1.medium.com/max/2600/0*jKU-wqVK-A6as8iU" width="5184"></a></p><p class="medium-feed-snippet">What is sampling bias in recommendation, and how to correct them</p><p class="medium-feed-link"><a href="https://medium.com/data-science/correct-sampling-bias-for-recommender-systems-d2f6d9fdddec?source=rss-a836aac352ca------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/correct-sampling-bias-for-recommender-systems-d2f6d9fdddec?source=rss-a836aac352ca------2</link>
            <guid isPermaLink="false">https://medium.com/p/d2f6d9fdddec</guid>
            <category><![CDATA[recommendations]]></category>
            <category><![CDATA[programming]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[neural-networks]]></category>
            <dc:creator><![CDATA[Thao Vu]]></dc:creator>
            <pubDate>Sun, 01 Oct 2023 15:16:04 GMT</pubDate>
            <atom:updated>2023-10-01T15:16:17.185Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[A Quick Guide on Normalization for Your NLP Model]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/a-quick-guide-on-normalization-for-your-nlp-model-2dbd7d2d42a7?source=rss-a836aac352ca------2"><img src="https://cdn-images-1.medium.com/max/2600/0*jUVYZrSd7ejLosOm" width="5184"></a></p><p class="medium-feed-snippet">Accelerate your model convergence and stabilize the training process with normalization</p><p class="medium-feed-link"><a href="https://medium.com/data-science/a-quick-guide-on-normalization-for-your-nlp-model-2dbd7d2d42a7?source=rss-a836aac352ca------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/a-quick-guide-on-normalization-for-your-nlp-model-2dbd7d2d42a7?source=rss-a836aac352ca------2</link>
            <guid isPermaLink="false">https://medium.com/p/2dbd7d2d42a7</guid>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[tips-and-tricks]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[large-language-models]]></category>
            <category><![CDATA[nlp]]></category>
            <dc:creator><![CDATA[Thao Vu]]></dc:creator>
            <pubDate>Thu, 14 Sep 2023 07:55:14 GMT</pubDate>
            <atom:updated>2023-09-14T07:55:14.855Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Build Your First Autocorrection without Machine Learning]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/build-your-first-autocorrection-without-machine-learning-31cf30af694a?source=rss-a836aac352ca------2"><img src="https://cdn-images-1.medium.com/max/2600/0*eG8DDk27LbngZMis" width="5760"></a></p><p class="medium-feed-snippet">A step-by-step guide to building your own spell checker.</p><p class="medium-feed-link"><a href="https://pub.towardsai.net/build-your-first-autocorrection-without-machine-learning-31cf30af694a?source=rss-a836aac352ca------2">Continue reading on Towards AI »</a></p></div>]]></description>
            <link>https://pub.towardsai.net/build-your-first-autocorrection-without-machine-learning-31cf30af694a?source=rss-a836aac352ca------2</link>
            <guid isPermaLink="false">https://medium.com/p/31cf30af694a</guid>
            <category><![CDATA[programming]]></category>
            <category><![CDATA[application]]></category>
            <category><![CDATA[nlp]]></category>
            <category><![CDATA[probability]]></category>
            <category><![CDATA[language]]></category>
            <dc:creator><![CDATA[Thao Vu]]></dc:creator>
            <pubDate>Sun, 03 Sep 2023 20:02:27 GMT</pubDate>
            <atom:updated>2023-09-03T20:02:27.752Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Guiding LLM with Reinforcement Learning from Human Feedback — Part 1]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@vuphuongthao9611/guiding-llm-with-reinforcement-learning-from-human-feedback-part-1-c8c0579f5a6f?source=rss-a836aac352ca------2"><img src="https://cdn-images-1.medium.com/max/1024/1*JkAepjcRfRP7d0PCsLJMnQ.png" width="1024"></a></p><p class="medium-feed-snippet">Ever wonder why ChatGPT won&#x2019;t tell you how to make a bomb?</p><p class="medium-feed-link"><a href="https://medium.com/@vuphuongthao9611/guiding-llm-with-reinforcement-learning-from-human-feedback-part-1-c8c0579f5a6f?source=rss-a836aac352ca------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@vuphuongthao9611/guiding-llm-with-reinforcement-learning-from-human-feedback-part-1-c8c0579f5a6f?source=rss-a836aac352ca------2</link>
            <guid isPermaLink="false">https://medium.com/p/c8c0579f5a6f</guid>
            <category><![CDATA[chatgpt]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[ml-so-good]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[llm]]></category>
            <dc:creator><![CDATA[Thao Vu]]></dc:creator>
            <pubDate>Mon, 28 Aug 2023 17:57:55 GMT</pubDate>
            <atom:updated>2023-08-28T17:57:55.260Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[BERT vs GPT: Comparing the NLP Giants]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/bert-vs-gpt-comparing-the-nlp-giants-329d105e34ec?source=rss-a836aac352ca------2"><img src="https://cdn-images-1.medium.com/max/1024/1*OOpmPNqmWE0J9EL9qeP16w.png" width="1024"></a></p><p class="medium-feed-snippet">How different are their structure, and how do the differences impact the model&#x2019;s ability?</p><p class="medium-feed-link"><a href="https://medium.com/data-science/bert-vs-gpt-comparing-the-nlp-giants-329d105e34ec?source=rss-a836aac352ca------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/bert-vs-gpt-comparing-the-nlp-giants-329d105e34ec?source=rss-a836aac352ca------2</link>
            <guid isPermaLink="false">https://medium.com/p/329d105e34ec</guid>
            <category><![CDATA[nlp]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[machine-learning]]></category>
            <dc:creator><![CDATA[Thao Vu]]></dc:creator>
            <pubDate>Sun, 20 Aug 2023 16:37:33 GMT</pubDate>
            <atom:updated>2023-08-20T16:38:03.142Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Leveraging LLMs with Information Retrieval: A Simple Demo]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/data-science/leveraging-llms-with-information-retrieval-a-simple-demo-600825d3cb4c?source=rss-a836aac352ca------2"><img src="https://cdn-images-1.medium.com/max/1024/1*TaVGrB4OVzjy45Lr7AhexA.png" width="1024"></a></p><p class="medium-feed-snippet">A demo of integrating a Question-Answering LLM with retrieval components</p><p class="medium-feed-link"><a href="https://medium.com/data-science/leveraging-llms-with-information-retrieval-a-simple-demo-600825d3cb4c?source=rss-a836aac352ca------2">Continue reading on TDS Archive »</a></p></div>]]></description>
            <link>https://medium.com/data-science/leveraging-llms-with-information-retrieval-a-simple-demo-600825d3cb4c?source=rss-a836aac352ca------2</link>
            <guid isPermaLink="false">https://medium.com/p/600825d3cb4c</guid>
            <category><![CDATA[chatgpt]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[llm]]></category>
            <category><![CDATA[deep-learning]]></category>
            <category><![CDATA[nlp]]></category>
            <dc:creator><![CDATA[Thao Vu]]></dc:creator>
            <pubDate>Mon, 14 Aug 2023 15:00:38 GMT</pubDate>
            <atom:updated>2023-08-14T15:00:38.890Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[A Quick Guide to Fine-tuning Techniques for Large Language Models]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/@vuphuongthao9611/a-simple-survey-of-fine-tuning-techniques-for-large-language-models-6c7945e6ee34?source=rss-a836aac352ca------2"><img src="https://cdn-images-1.medium.com/max/610/1*shsCW_F1LLqGzao5-PJpBA.png" width="610"></a></p><p class="medium-feed-snippet">Large language models (LLM) have transformed the field of natural language processing (NLP) with their remarkable text understanding and&#x2026;</p><p class="medium-feed-link"><a href="https://medium.com/@vuphuongthao9611/a-simple-survey-of-fine-tuning-techniques-for-large-language-models-6c7945e6ee34?source=rss-a836aac352ca------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://medium.com/@vuphuongthao9611/a-simple-survey-of-fine-tuning-techniques-for-large-language-models-6c7945e6ee34?source=rss-a836aac352ca------2</link>
            <guid isPermaLink="false">https://medium.com/p/6c7945e6ee34</guid>
            <category><![CDATA[large-language-models]]></category>
            <category><![CDATA[ml-so-good]]></category>
            <category><![CDATA[transformers]]></category>
            <category><![CDATA[nlp]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <dc:creator><![CDATA[Thao Vu]]></dc:creator>
            <pubDate>Sat, 15 Jul 2023 07:37:35 GMT</pubDate>
            <atom:updated>2023-08-02T12:16:32.229Z</atom:updated>
        </item>
    </channel>
</rss>