<p>In this episode, we're covering two papers on zero-shot forecasting: NXAI's TiRex and Amazon's Chronos-2. You may be asking… Is it pronounced tee·rɛks? Is it tye·rɛks? Is it a titan? God of time? Is a time series just a sequence? Is a sequence just a sentence? Is time a sentence? Is time a poem? As a poem constellates images, and an LLM strings together tokens, the authors apply this approach to time series forecasting, offering new opportunities for zero-shot weather prediction.</p>
<p>We discuss the history of the term "Zero-shot," breakdown each paper from training data to industry applications, and wax poetic about the paradigm shift these models are bringing to earth systems forecasting.</p>
<hr>
<h2>Papers</h2>
<ul>
<li><strong><a href="https://arxiv.org/abs/2502.00479">TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning</a></strong>, Auer et al</li>
<li><strong><a href="https://arxiv.org/abs/2410.04220">Chronos-2: From Univariate to Universal Forecasting</a></strong>, Ansari et al</li>
</ul>
<hr>
<h2>Recommended reading</h2>
<ul>
<li><em>The Crying of Lot 49</em> by Thomas Pynchon</li>
<li><em>God, Human, Animal, Machine: Technology, Metaphor, and the Search for Meaning</em> by Meghan O'Gieblyn</li>
<li><em>The Odyssey</em> by Homer (Translated by Emily Wilson)</li>
<li><em>The Hainish Cycle</em> series by Ursula K. Le Guin</li>
</ul>
