<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Machine-Learning on Sparse Notes</title>
    <link>https://sparsenotes.com/tags/machine-learning/</link>
    <description>Recent content in Machine-Learning on Sparse Notes</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <copyright>© 2026 Pradithya Aria Pura</copyright>
    <lastBuildDate>Sat, 21 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://sparsenotes.com/tags/machine-learning/index.xml" rel="self" type="application/rss+xml" />
    
    <item>
      <title>K2-Horizon: A Frontier Fleet of Open Source Language Models</title>
      <link>https://sparsenotes.com/posts/2026/11/papers/k2-horizon-open-frontier-fleet/</link>
      <pubDate>Sat, 21 Nov 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/11/papers/k2-horizon-open-frontier-fleet/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Unbundling Multimodal Vision Encoding</title>
      <link>https://sparsenotes.com/posts/2026/11/papers/unbundling-multimodal-vision-encoding/</link>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/11/papers/unbundling-multimodal-vision-encoding/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Hinted Scaling Laws</title>
      <link>https://sparsenotes.com/posts/2026/11/papers/hinted-scaling-laws/</link>
      <pubDate>Sat, 07 Nov 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/11/papers/hinted-scaling-laws/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Learning Representations by Back-propagating Errors (Rumelhart, Hinton &amp; Williams, 1986)</title>
      <link>https://sparsenotes.com/posts/2026/11/papers/backpropagation-rumelhart-hinton-williams-1986/</link>
      <pubDate>Sat, 07 Nov 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/11/papers/backpropagation-rumelhart-hinton-williams-1986/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Proving and Improving the Platonic Representation Hypothesis with JEPAs</title>
      <link>https://sparsenotes.com/posts/2026/10/papers/platonic-representation-theorem-jepa/</link>
      <pubDate>Sat, 31 Oct 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/10/papers/platonic-representation-theorem-jepa/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>A Fix for Softmax and Cross-Entropy</title>
      <link>https://sparsenotes.com/posts/2026/10/papers/softmax-cross-entropy-numerical-fix/</link>
      <pubDate>Sat, 24 Oct 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/10/papers/softmax-cross-entropy-numerical-fix/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>An Observation on Generalization</title>
      <link>https://sparsenotes.com/posts/2026/08/unsupervised-learning-compression-sutskever/</link>
      <pubDate>Sat, 29 Aug 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/08/unsupervised-learning-compression-sutskever/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>LeVJEPA: Efficient &amp; Scalable Video Pretraining without the Heuristics</title>
      <link>https://sparsenotes.com/posts/2026/08/papers/levjepa-video-pretraining/</link>
      <pubDate>Sat, 29 Aug 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/08/papers/levjepa-video-pretraining/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Why Transformers Hit a Wall the Moment Physics Shows Up</title>
      <link>https://sparsenotes.com/posts/2026/08/neural-operators-physics-ai-anandkumar/</link>
      <pubDate>Sat, 29 Aug 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/08/neural-operators-physics-ai-anandkumar/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Let&#39;s Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts</title>
      <link>https://sparsenotes.com/posts/2026/08/papers/mup-hyperparameter-transfer-moe/</link>
      <pubDate>Sat, 22 Aug 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/08/papers/mup-hyperparameter-transfer-moe/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Synthetic Persona Pretraining: Alignment from Token Zero</title>
      <link>https://sparsenotes.com/posts/2026/08/papers/synthetic-persona-pretraining-alignment-token-zero/</link>
      <pubDate>Sat, 15 Aug 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/08/papers/synthetic-persona-pretraining-alignment-token-zero/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>OpenForgeRL: Train Harness-native Agents in Any Environment</title>
      <link>https://sparsenotes.com/posts/2026/07/papers/openforgerl-harness-native-agents/</link>
      <pubDate>Sat, 25 Jul 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/07/papers/openforgerl-harness-native-agents/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Windowed-MTP: Removing the Full-Context Draft-KV Tax at Million-Token Context</title>
      <link>https://sparsenotes.com/posts/2026/07/papers/windowed-mtp-draft-kv-tax/</link>
      <pubDate>Sat, 25 Jul 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/07/papers/windowed-mtp-draft-kv-tax/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Super Weights in LLMs and the Failure of Selective Training</title>
      <link>https://sparsenotes.com/posts/2026/07/papers/super-weights-2607.08733/</link>
      <pubDate>Sat, 11 Jul 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/07/papers/super-weights-2607.08733/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Hallucination in World Models is Predictable and Preventable</title>
      <link>https://sparsenotes.com/posts/2026/06/papers/2026-06-27-world-model-hallucination/</link>
      <pubDate>Sat, 27 Jun 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/06/papers/2026-06-27-world-model-hallucination/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models</title>
      <link>https://sparsenotes.com/posts/2026/06/papers/2026-06-27-co-failure-ceiling/</link>
      <pubDate>Sat, 27 Jun 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/06/papers/2026-06-27-co-failure-ceiling/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers</title>
      <link>https://sparsenotes.com/posts/2026/06/papers/2026-06-13-clipping-asgd-stragglers/</link>
      <pubDate>Sat, 13 Jun 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/06/papers/2026-06-13-clipping-asgd-stragglers/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Pretraining Recurrent Networks without Recurrence</title>
      <link>https://sparsenotes.com/posts/2026/06/papers/2026-06-06-smt-rnn-without-recurrence/</link>
      <pubDate>Sat, 06 Jun 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/06/papers/2026-06-06-smt-rnn-without-recurrence/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>You Only Index Once: Cross-Layer Sparse Attention with Shared Routing</title>
      <link>https://sparsenotes.com/posts/2026/06/papers/2026-06-06-clsa-cross-layer-sparse-attention/</link>
      <pubDate>Sat, 06 Jun 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/06/papers/2026-06-06-clsa-cross-layer-sparse-attention/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Attention Is All You Need (2017): The Architecture That Ate Machine Learning</title>
      <link>https://sparsenotes.com/posts/2026/05/papers/2026-05-30-attention-is-all-you-need/</link>
      <pubDate>Sat, 30 May 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/05/papers/2026-05-30-attention-is-all-you-need/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>On Language Generation in the Limit with Bounded Memory</title>
      <link>https://sparsenotes.com/posts/2026/05/papers/2026-05-30-bounded-memory-generation/</link>
      <pubDate>Sat, 30 May 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/05/papers/2026-05-30-bounded-memory-generation/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Reasoning in Memory: Latent Reasoning Without Autoregressive Thoughts</title>
      <link>https://sparsenotes.com/posts/2026/05/papers/2026-05-30-rim-working-memory/</link>
      <pubDate>Sat, 30 May 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/05/papers/2026-05-30-rim-working-memory/</guid>
      <description></description>
      
    </item>
    
    <item>
      <title>Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention</title>
      <link>https://sparsenotes.com/posts/2026/05/papers/2026-05-23-gated-deltanet-2/</link>
      <pubDate>Sat, 23 May 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/05/papers/2026-05-23-gated-deltanet-2/</guid>
      <description></description>
      
    </item>
    
  </channel>
</rss>
