Skill UI

A comprehensive guide for computer vision researchers to determine if their project is a good fit for ECCV, considering scope, technical durability, and academic timing. It weighs the project's contribution against the specific requirements of ECCV versus competing top-tier venues like CVPR and ICCV, ensuring strategic submission planning.

A comprehensive guide for researchers submitting NLP papers, detailing best practices for achieving high reproducibility. It instructs users to pin model versions, log data provenance, report compute costs, and adhere rigorously to the Responsible NLP checklist. Essential for ensuring academic integrity and enabling rigorous verification of ML experiments.

A comprehensive guide detailing the strict requirements for submitting research papers to EMNLP via the ACL Rolling Review (ARR). Key areas covered include template compliance, page length restrictions (long/short format), mandatory limitations sections, double-blind anonymization techniques, and adherence to the Responsible NLP checklist. Use this audit guide before submission to ensure full compliance and avoid desk-rejects.

This guide outlines best practices for structuring advanced NLP/AI research papers for academic submission. It details the critical differences between core content pages, mandatory limitations sections, discretionary appendices, and supplementary uploads, ensuring that reviewers are properly guided and that the work remains reproducible and verifiable.

A comprehensive guide detailing the empirical writing style required for EMNLP submissions. It emphasizes scoping claims to specific datasets and languages, ensuring examples are load-bearing, structuring the argument phenomenon-first, and accurately calibrating hedging language based on evidence strength.

This guide provides a comprehensive strategy for authors submitting NLP and Computational Linguistics papers to EACL. It covers conference positioning, manuscript re-framing from journal or arXiv styles, and establishes rigorous evidence standards. It helps authors ensure their work aligns with the European ACL community focus, optimizing the paper's narrative structure for high acceptance rates.

This skill facilitates the loading and application of relevant historical experience memories (OpenViking memories) before executing task actions. It guides the user through a rigorous process: querying memories, applying strict applicability and exclusion checks (gating), and prioritizing real-time facts over loaded guidance. Essential for complex, multi-intent conversational flows.

A comprehensive guide to preparing accountability artifacts for AI research papers, particularly for venues like FAccT. It covers the necessary documentation genres—including datasheets for datasets, model cards for models, and impact assessments—to ensure transparency, verifiability, and accountability regarding claims of fairness and harm mitigation in AI systems. The focus is on making research outputs rigorously traceable and ethically responsible.

This comprehensive guide outlines the critical steps required for authors preparing an accepted paper for ACM FAccT proceedings. It details the transition from anonymous drafts to the final, published 'camera-ready' format, covering mandatory de-anonymization (restoring author details and adding Positionality statements), switching to the specific ACM metadata standards (ORCID, CCS concepts), completing required documentation (datasheets/model cards), and adhering to complex publication timelines and rights requirements.

This guide outlines the rigorous methodological standards for empirical work in AI fairness, accountability, and transparency (FAccT). It advises researchers on matching specific claims (e.g., disparate harm) to appropriate evidence types—including disaggregated metrics, coded qualitative data, and documented ethical procedures. It stresses the importance of ethical review, handling protected attributes, and acknowledging limitations to ensure high scientific and ethical rigor.

A comprehensive guide for establishing academic rigor in AI and data science research. It outlines best practices for achieving reproducibility, emphasizing the mandatory release and documentation of raw data, trained models, and qualitative findings. Key tools include datasheets, model cards, and detailed provenance logging, ensuring that research claims are fully auditable and consistent.

This guide helps researchers determine the most appropriate academic venue for their responsible AI work. It provides detailed criteria and rigorous testing methods (like the Delete-the-equity test) to assess whether fairness, accountability, or transparency is a primary, core contribution, guiding authors away from merely 'bolted-on' ethical framing.