icml-related-work
Use when positioning an ICML submission against close ML literature, concurrent ICML submissions, recent public papers, workshop papers, ICLR/AISTATS/NeurIPS neighbors, and prior work under double-blind constraints.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill icml-related-work --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# ICML Related Work Use this when novelty, incremental contribution, or concurrent-submission handling is the risk. ICML 2026 treats related concurrent ICML submissions with overlapping authors as prior work. ## Required coverage - Closest ML methods, theory, datasets, benchmarks, and evaluation papers. - Neighboring venue papers from NeurIPS, ICLR, AISTATS, UAI, COLT, MLSys, KDD, ACL, CVPR, and other relevant areas. - Related concurrent ICML submissions by overlapping authors; cite anonymously and include PDFs in supplementary material when a reasonable reviewer would expect them. - Workshop papers without published proceedings generally do not trigger dual-submission violation, but their relationship still needs honest positioning. - Very recent public work close to the full-paper deadline can be treated as concurrent, but good judgment and subfield norms matter. ## Delta paragraph ```text <Prior work> addresses <problem> using <mechanism>. It leaves <specific gap>. Our submission differs by <technical delta>, and this matters because <evidence>. ``` ## Novelty-pushback table (ICML reviewer reflexes) ICML reviewers triage novelty fast because the load is heavy and the first PMLR
- Required coverage
- Delta paragraph
- Novelty-pushback table (ICML reviewer reflexes)
- Worked vignette: a new optimizer with convergence theory
- Output format
What does the icml-related-work skill do?
Use when positioning an ICML submission against close ML literature, concurrent ICML submissions, recent public papers, workshop papers, ICLR/AISTATS/NeurIPS neighbors, and prior work under double-blind constraints.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill icml-related-work --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Awesome-Journal-Skills, a repository with 984 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.