{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidudd6hm2qlndjafbmjhc5pagksgjx4ojzlqxputj2khrmf7p6hnu",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mh3t64czh3u2"
  },
  "path": "/t/arxiv-endorsement-request-cs-lg-machine-learning/174272#post_1",
  "publishedAt": "2026-03-15T09:13:10.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "https://doi.org/10.5281/zenodo.19029046",
    "https://orcid.org/0009-0001-3287-3055"
  ],
  "textContent": "Hello everyone,\n\nMy name is **Ahmad Shajahan** , a 2nd-year B.Tech Computer Science student at **APJ Abdul Kalam Technological University, Kerala, India**.\n\nI have recently completed an original research paper titled:\n\n**“Thermodynamic Neural Computation (TNC): Novel Free-Energy Minimisation with Cache-Aware Memory-Mapped Annealing for Energy-Efficient AI.”**\n\nThe paper proposes a new computational framework where **gradient descent is replaced by thermodynamic free-energy minimisation** , introducing **14 novel equations** aimed at improving energy efficiency in AI training.\n\nKey idea:\nUsing thermodynamic principles and cache-aware annealing mechanisms to achieve significantly more **energy-efficient optimization compared to standard SGD**.\n\nThe paper is publicly available on Zenodo:\nhttps://doi.org/10.5281/zenodo.19029046\n\nORCID:\nhttps://orcid.org/0009-0001-3287-3055\n\nI am preparing to submit this work to **arXiv (cs.LG – Machine Learning)** , but as a first-time submitter I require an **endorsement from an existing arXiv author**.\n\nIf anyone eligible to endorse in **cs.LG** is willing to review or endorse the submission, I would be very grateful.\n\nI would be happy to share the full manuscript or discuss the work.\n\nThank you very much for your time and support.\n\n— Ahmad Shajahan",
  "title": "arXiv Endorsement Request — cs.LG (Machine Learning)"
}