index.html

<!doctype html>
<html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1">
<title>Home · Anirban Pal</title><meta name="description" content="Anirban Pal, PhD researcher at IIT Bombay Monash. Machine learning, biology, and drug discovery; representation and continual learning, foundation models, and biological and molecular representation learning.">
<link rel="canonical" href="https://alphago1234.github.io/"><link rel="icon" href="assets/favicon.svg" type="image/svg+xml">
<meta property="og:type" content="website"><meta property="og:title" content="Home · Anirban Pal">
<meta property="og:description" content="Anirban Pal, PhD researcher at IIT Bombay Monash. Machine learning, biology, and drug discovery; representation and continual learning, foundation models, and biological and molecular representation learning."><meta property="og:url" content="https://alphago1234.github.io/">
<meta property="og:image" content="https://alphago1234.github.io/assets/portrait.png"><meta name="theme-color" content="#fcfbf8">
<link rel="stylesheet" href="assets/style.css"><script src="assets/site.js" defer></script>
<script type="application/ld+json">{"@context": "https://schema.org", "@type": "Person", "name": "Anirban Pal", "url": "https://alphago1234.github.io", "jobTitle": "PhD researcher", "image": "https://alphago1234.github.io/assets/portrait.png", "sameAs": ["https://github.com/alphago1234", "https://openreview.net/profile?id=~Anirban_Pal2", "https://www.linkedin.com/in/anirban-pal-26049a2a6/", "https://www.researchgate.net/profile/Anirban-Pal-18"], "knowsAbout": ["Representation learning", "Continual learning", "Self-supervised learning", "Foundation models", "Machine learning for biology", "Molecular design", "Catalysis"]}</script></head>
<body id="top"><a class="skip" href="#main">Skip to content</a><div class="layout">
<aside class="sidebar" aria-label="Profile and site navigation">
  <img class="portrait" src="assets/portrait.png" alt="Anirban Pal" width="144" height="144">
  <a class="identity" href="index.html">Anirban Pal</a>
  <p class="affiliation">PhD researcher at<br>IIT Bombay Monash<br>Mumbai, India</p>
  <nav class="nav" aria-label="Main navigation"><a href="index.html" aria-current="page">Home</a><a href="research.html">Research</a><a href="publications.html">Publications</a><a href="code.html">Code</a><a href="contact.html">Contact</a></nav>
  <div class="socials"><a href="https://github.com/alphago1234">GitHub ↗</a><a href="https://openreview.net/profile?id=~Anirban_Pal2">OpenReview ↗</a><a href="mailto:anirban.nayan@gmail.com">Email ↗</a></div>
  <p class="sidebar-note">Representation learning<br>Machine learning for science</p>
</aside>
<main id="main"><p class="eyebrow">MACHINE LEARNING · BIOLOGY · DRUG DISCOVERY</p>
<h1>Learning representations<br>that remain useful.</h1>
<div class="intro"><p>I&#x27;m Anirban Pal, a PhD researcher at IIT Bombay Monash Research Academy working across machine learning, biology, and drug discovery. I study how models learn useful representations, retain knowledge, and generalize under distribution shift.</p><p>My research spans continual learning, self-supervised learning, and foundation models, alongside biological and molecular representation learning for cancer research, drug discovery, and catalysis.</p></div>
<p class="home-cta"><a href="research.html">Explore my research →</a></p>
<section class="section" aria-labelledby="directions"><div class="section-head"><h2 id="directions">Research directions</h2></div>
<div class="themes">
<article class="theme"><span class="number">01</span><h3>Representations &amp; continual learning</h3><p>Representation drift, feature alignment, and knowledge retention as models and data change.</p></article>
<article class="theme"><span class="number">02</span><h3>Foundation models &amp; world models</h3><p>Self-supervised features, latent prediction, and adaptation of pretrained representations.</p></article>
<article class="theme"><span class="number">03</span><h3>Biological and Molecular Representation Learning</h3><p>Learning from biological and chemical data for cancer research, drug discovery, and catalysis.</p></article>
</div></section>
<section class="section" aria-labelledby="selected"><div class="section-head"><h2 id="selected">Selected work</h2><a href="publications.html">All publications →</a></div><article class="pub" id="foundation-model-work"><h3>Foundation-model representations</h3>
<div class="pub-meta"><span class="status">Ongoing research</span></div>
<p class="abstract-line">Studying what pretrained representations retain, how they change during adaptation, and how they transfer to downstream tasks. This work connects self-supervised learning and JEPA-based world models with continual learning and biological and molecular applications.</p>
<div class="pub-links"><a href="research.html#foundation-models">Research direction →</a></div></article><article class="pub" id="repairable-geometry" data-publication data-category="accepted">
      <h3>The Interface Contract: Repairable Geometry and Partially Predictable Drift in Continual Representation Learning</h3><p class="authors">Atharva Airen, <strong>Anirban Pal</strong></p>
      <div class="pub-meta"><span class="status accepted">NeurIPS 2026 Workshop NeurIPS Extended Abstracts</span> 2026</div>
      <div class="pub-links"><a href="https://openreview.net/profile?id=~Anirban_Pal2">Author profile ↗</a></div></article><article class="pub" id="pixel-reconstruction" data-publication data-category="accepted">
      <h3><a href="https://openreview.net/forum?id=PMjBo6Ii83">Pixel Reconstruction Keeps an Absolute-Coordinate Channel that Latent Prediction Lets Go</a></h3><p class="authors">Aarav Gupta, <strong>Anirban Pal</strong></p>
      <div class="pub-meta"><span class="status accepted">CAISc 2026 · accepted paper</span> 2026</div>
      <div class="pub-links"><a href="https://openreview.net/forum?id=PMjBo6Ii83">OpenReview ↗</a> <a href="https://caisc2026.github.io/accepted_papers.html">Conference listing ↗</a></div></article><article class="pub" id="latent-planning" data-publication data-category="accepted">
      <h3><a href="https://openreview.net/forum?id=ieS8kpFAuG">Action-Conditioned Sparsity for Latent-Space Planning</a></h3><p class="authors">Aarav Gupta, <strong>Anirban Pal</strong></p>
      <div class="pub-meta"><span class="status accepted">CAISc 2026 · accepted paper</span> 2026</div>
      <div class="pub-links"><a href="https://openreview.net/forum?id=ieS8kpFAuG">OpenReview ↗</a> <a href="https://caisc2026.github.io/accepted_papers.html">Conference listing ↗</a></div></article><article class="pub" id="vector-plus" data-publication data-category="preprint">
      <h3><a href="https://arxiv.org/abs/2509.00684">Valid Property-Enhanced Contrastive Learning for Targeted Optimization &amp; Resampling for Novel Drug Design</a></h3><p class="authors">Amartya Banerjee, Somnath Kar, <strong>Anirban Pal</strong>, Debabrata Maiti</p>
      <div class="pub-meta"><span class="status preprint">arXiv preprint</span> 2025</div>
      <div class="pub-links"><a href="https://arxiv.org/abs/2509.00684">Paper ↗</a> <a href="https://arxiv.org/pdf/2509.00684">PDF ↗</a> <a href="https://github.com/amartya21/vector-drug-design">Code ↗</a></div></article><article class="pub" id="pyridines-from-nitroarenes" data-publication data-category="journal">
      <h3><a href="https://doi.org/10.1002/anie.202517867">A General Strategy to Access Pharmaceutically Relevant Pyridines from Nitroarenes</a></h3><p class="authors">Argha Saha, Avishek Pan, Devika Ghosh, <strong>Anirban Pal</strong>, Srimanta Guin, Archana Kumari Redhu, Vikram Gota, Debabrata Maiti</p>
      <div class="pub-meta"><span class="status journal">Published journal article</span> Angewandte Chemie International Edition · 2026, 65(6), e17867</div>
      <p class="note">First online: 24 December 2025; issue date: 2 February 2026</p><div class="pub-links"><a href="https://doi.org/10.1002/anie.202517867">Paper ↗</a></div></article><article class="pub" id="picolinamide-chalcogenation" data-publication data-category="journal">
      <h3><a href="https://doi.org/10.1039/d4sc07897g">Generating the Pd-catalyzed δ C–H chalcogenation of aliphatic picolinamides: systematically decreasing the bias</a></h3><p class="authors">Soumya Kumar Sinha, Aniket Gholap, Yazhinimuthu C M, <strong>Anirban Pal</strong>, Anant R. Kapdi, Debabrata Maiti</p>
      <div class="pub-meta"><span class="status journal">Published journal article</span> Chemical Science · 2025, 16(18), 7936–7945</div>
      <div class="pub-links"><a href="https://doi.org/10.1039/d4sc07897g">Paper ↗</a> <a href="https://pubs.rsc.org/en/content/articlepdf/2025/sc/d4sc07897g">PDF ↗</a></div></article></section><section class="section" aria-labelledby="news"><div class="section-head"><h2 id="news">Recent work</h2></div>
<ul class="news"><li><time>2026</time><span>Two papers with Aarav Gupta on latent prediction and latent-space planning appear in the <a href="https://caisc2026.github.io/accepted_papers.html">CAISc accepted-paper list</a>.</span></li>
<li><time>2026</time><span>Work with Atharva Airen examines representation drift, test-time feature alignment, gradient reuse, and retrieval compatibility. <a href="publications.html">Publication records →</a></span></li>
<li><time>2025</time><span><a href="https://arxiv.org/abs/2509.00684">VECTOR+</a> introduces property-guided contrastive learning and latent-space sampling for molecular design.</span></li></ul></section><footer class="footer"><span>© 2026 Anirban Pal · Updated October 2026</span>
<a class="back-top" href="#top">Back to top ↑</a></footer></main></div></body></html>