<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Ai Research on Tenu Tech Brief</title>
    <link>https://cluster-site.onrender.com/tags/ai-research/</link>
    <description>Recent content in Ai Research on Tenu Tech Brief</description>
    <generator>Hugo -- 0.146.0</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 24 Feb 2026 06:06:03 +0000</lastBuildDate>
    <atom:link href="https://cluster-site.onrender.com/tags/ai-research/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Federated Reasoning Distillation Framework with Model Learnability-Aware Data Allocation</title>
      <link>https://cluster-site.onrender.com/posts/federated-reasoning-distillation-framework-with-model-learnability-aware-data-allocation/</link>
      <pubDate>Tue, 24 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/federated-reasoning-distillation-framework-with-model-learnability-aware-data-allocation/</guid>
      <description>• Addresses bidirectional model learnability gap in federated LLM-SLM reasoning collaboration. • Introduces LaDa framework with learnability-aware data filter for high-reward sampl</description>
    </item>
    <item>
      <title>Prompt Optimization Via Diffusion Language Models</title>
      <link>https://cluster-site.onrender.com/posts/prompt-optimization-via-diffusion-language-models/</link>
      <pubDate>Tue, 24 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/prompt-optimization-via-diffusion-language-models/</guid>
      <description>• Diffusion-based framework refines system prompts via masked denoising in an iterative manner. • Conditions on interaction traces: user queries, model responses, and optional feed</description>
    </item>
    <item>
      <title>Replication Study: Federated Text-Driven Prompt Generation for Vision-Language Models</title>
      <link>https://cluster-site.onrender.com/posts/replication-study-federated-text-driven-prompt-generation-for-vision-language-models/</link>
      <pubDate>Tue, 24 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/replication-study-federated-text-driven-prompt-generation-for-vision-language-models/</guid>
      <description>• FedTPG introduces dynamic text-driven prompt generation for vision-language models in federated settings. • Replication evaluated on six datasets, achieving 74.58% seen, 76.00% u</description>
    </item>
    <item>
      <title>Simple Baselines are Competitive with Code Evolution</title>
      <link>https://cluster-site.onrender.com/posts/simple-baselines-are-competitive-with-code-evolution/</link>
      <pubDate>Fri, 20 Feb 2026 05:00:00 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/simple-baselines-are-competitive-with-code-evolution/</guid>
      <description>• Code evolution uses LLMs to mutate code, yet lacks baseline comparisons. • Authors test two simple baselines across math bounds, agentic scaffolds, and ML contests. • Baselines m</description>
    </item>
    <item>
      <title>Vulnerabilities in Popular PDF Platforms Allowed Account Takeover, Data Exfiltration</title>
      <link>https://cluster-site.onrender.com/posts/vulnerabilities-in-popular-pdf-platforms-allowed-account-takeover-data-exfiltration/</link>
      <pubDate>Wed, 18 Feb 2026 13:16:19 +0000</pubDate>
      <guid>https://cluster-site.onrender.com/posts/vulnerabilities-in-popular-pdf-platforms-allowed-account-takeover-data-exfiltration/</guid>
      <description>• 16 critical, high, and medium‑severity vulnerabilities found in Foxit and Apryse PDF platforms. • Flaws include DOM XSS, SSRF, path traversal, and OS command injection. • Attacke</description>
    </item>
  </channel>
</rss>
