Skill UI

A comprehensive guide for authors submitting to major signal processing conferences like ICASSP. It details how to audit, define, and precisely position a paper's novelty by comparing it against specific literature lanes (SPS journals, conferences, and ML venues). Learn to articulate the technical delta against the nearest work in a constrained, four-page format.

This guide details the best practices for packaging, documenting, and releasing research artifacts (code, models, data) for top-tier ML conferences. It covers two stages: preparing a non-identifiable archive for anonymous review, and managing the public release runway, focusing on reproducibility, licensing, and sustained maintenance.

This guide provides comprehensive best practices for designing and auditing empirical experiments for top-tier ML conferences. It covers necessary ablations, robustness checks (e.g., data shift, seeds), fair baselines, and detailed compute reporting to ensure that reported gains are scientifically genuine, reproducible, and address common reviewer skepticism.

A comprehensive guide for academic authors detailing how to establish and maintain rigorous reproducibility in Machine Learning research papers (e.g., ICLR). It instructs on mapping every central claim to verifiable evidence, including recording seeds, variance, specific compute budgets (training vs. inference), data preprocessing scripts, and ethical considerations. The statement must function as a public contract for the scientific community.

This guide provides essential instructions for authors submitting research to the ECAI conference, focusing on creating credible and reproducible artifacts. It strongly cautions authors about misconceptions regarding separate artifact badges, emphasizing that credibility must be built into the paper and supplement for direct reviewer judgment. Guidelines are provided for matching the artifact (code, proofs, data) to the specific contribution type (Theory, ML, Optimization).

Provides comprehensive guidelines for packaging supplementary materials, including code, data, model weights, and benchmarks, for major machine learning conferences like ICML. It details the requirements for both the double-blind review stage (focusing on anonymization and minimal replication commands) and the final public release package (ensuring permanent public links and clear licensing).

A comprehensive guide for authors on drafting strategic, anonymous rebuttals and discussion replies for top-tier Machine Learning conferences like ICML. Learn how to triage reviewer objections by focusing on soundness, originality, significance, clarity, ethics, and reproducibility, adhering strictly to double-blind review constraints and maximizing impact in limited discussion rounds.

Provides a comprehensive guide for preparing an accepted academic paper for camera-ready submission, detailing the necessary steps after acceptance. This workflow covers de-anonymization, integrating reviewer feedback, writing lay summaries, running format checks, and managing public-facing records such as reviews and conflict disclosures, ensuring publication readiness for top-tier conferences.

This guide provides a comprehensive framework for stress-testing Machine Learning experimental evidence before submission or rebuttal. It covers critical areas such as establishing strong baselines, conducting mechanism-isolating ablations, reporting variance, checking for data leakage, and disclosing compute costs. Use this to ensure your ML claims are scientifically sound, robust, and fair against rigorous academic scrutiny.

A comprehensive guide for researchers detailing how to strengthen the reproducibility of AI/ML papers for top-tier conferences like ICML. It provides an evidence checklist covering data sources, anonymized code, random seeds, compute budget disclosure, and theoretical assumptions, ensuring claims are robust and verifiable.

A comprehensive audit checklist for ensuring final submissions to the ICML conference. It verifies compliance across critical areas including LaTeX formatting, strict page limits, double-blind anonymity, impact statements, dual submission rules, and adherence to the latest LLM and ethical policies. Essential for researchers preparing papers for top-tier AI venues.

This guide outlines the proper placement of various research materials—including proofs, code, and extended results—within major academic conference submissions. It helps authors understand which content must be presented in the main body, which belongs in appendices, and how to correctly manage supplementary manuscripts and code/data supplements to maximize the chance of reviewer acceptance.