{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreigyn6qitcmsa2ioshful3q3iivtgmkd62l23igoy36afkcgjp6osi",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mjphazh5uck2"
  },
  "path": "/t/independent-researcher-looking-for-technical-feedback-on-a-paper-about-a-revision-capable-language-model/175347#post_1",
  "publishedAt": "2026-04-17T16:32:43.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "Reviser/main.pdf at main · Sean-Diab/Reviser · GitHub",
    "Log in to arXiv | arXiv e-print repository"
  ],
  "textContent": "Hi everyone! I am an independent researcher working on Reviser, a language model that generates through cursor-relative edit actions on a mutable canvas. It is autoregressive over edit-history actions rather than final text order, which lets it revise its response while keeping decoding efficiency close to standard autoregressive transformers.\n\nMy goal is to submit the paper to a conference such as ACL, EMNLP, ICML, or a similar venue, and I would really appreciate technical feedback on things like:\n\n  * Boldness/strength of the claims\n  * Weaknesses\n  * Quality of the results, or if I should include other results\n\n\n\nPaper: Reviser/main.pdf at main · Sean-Diab/Reviser · GitHub\n\nI would really value any feedback on what I should improve before submitting.\n\nI am also looking for an arXiv endorsement for cs.CL. If anyone here is eligible and feels comfortable helping, my endorsement link is: Log in to arXiv | arXiv e-print repository\n\nThank you very much.",
  "title": "Independent researcher looking for technical feedback on a paper about a revision-capable language model"
}