Skill UI

Writes rigorous mathematical proofs for ML/AI theory, including theorem/lemma drafting, filling missing proof steps, formalizing proof sketches, and checking whether claims are provable from assumptions.

Reads a LaTeX proof, finds gaps via cross-model adversarial review, fixes each gap with full derivations, re-reviews until convergence, and outputs an audit report with proof-obligation accounting.

Generate comprehensive Chinese interview preparation cheat sheets for ML/LLM topics including mathematical formulas with derivations, from-scratch PyTorch implementations, comparison tables, and 25 high-frequency interview questions across L1/L2/L3 difficulty levels. Supports balanced or max effort modes with cross-model review.

This guide details the rigorous, mathematically focused peer-review pipeline for top ML conferences like COLT (Conference on Learning Theory). It explains the double-anonymous review system, how reviewers assess correctness, significance, and novelty, and provides actionable advice on structuring rebuttals and interpreting final decisions for researchers aiming for top-tier academic publication.

This guide assists researchers in determining the optimal venue for their theoretical machine learning contributions. It provides a framework for evaluating whether a result is best suited for COLT, or if it belongs in other top-tier conferences (e.g., NeurIPS, ICML) or journals (e.g., JMLR). It emphasizes differentiating between rigorous mathematical proofs (bounds, separations) and purely empirical findings.

A comprehensive style guide and checklist for writing and refining long-form academic articles for 'Pattern Recognition and Artificial Intelligence' (PR&AI). It covers the entire publishing workflow, from mastering the structured introduction (Problem-Gap-Contribution) and writing four-element abstracts, to adhering to rigorous standards for citations (GB/T 7714), figures, and mathematical notation in AI research.