// Use when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packages for a specific venue template, or configure compilation. Triggers on phrases like "setup latex", "biber vs bibtex", "latex compilation error", "install latex packages", "venue template", or "texlive setup".
| name | latex-setup |
| description | Use when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packages for a specific venue template, or configure compilation. Triggers on phrases like "setup latex", "biber vs bibtex", "latex compilation error", "install latex packages", "venue template", or "texlive setup". |
You are helping a researcher set up or fix their LaTeX compilation environment. Do NOT hardcode package lists — detect and install what's actually needed.
Before installing anything:
Check installed TeX distribution:
which pdflatex && pdflatex --version
which xelatex && xelatex --version
which lualatex && lualatex --version
Check bibliography processor:
which biber && biber --version
which bibtex && bibtex --version
Check package manager:
which tlmgr && tlmgr --version
Read the main .tex file to determine requirements:
\documentclass{article}, \documentclass{IEEEtran}, etc.\usepackage{biblatex} → needs biber\usepackage{natbib} or \bibliographystyle{...} → needs bibtex\usepackage{...} declarationsIf the user mentions a venue, search for the official template:
Common venues and their requirements:
| Venue | Class | Bib system | Notes |
|---|---|---|---|
| CVPR/ECCV | Custom class file | bibtex | Usually provided in template |
| NeurIPS | neurips_20XX.sty | natbib + bibtex | Style file changes yearly |
| ICLR | iclr20XX_conference.sty | natbib + bibtex | OpenReview format |
| ACL/EMNLP | acl.cls | bibtex | ACL Anthology format |
| IEEE | IEEEtran.cls | bibtex | Column formatting specific |
| Springer | llncs.cls | bibtex or biblatex | Depends on series |
Based on analysis, install only what's missing:
# Base installation (if nothing installed)
sudo apt install texlive-base texlive-latex-recommended
# Common extras
sudo apt install texlive-latex-extra # most \usepackage needs
sudo apt install texlive-fonts-recommended texlive-fonts-extra
sudo apt install texlive-bibtex-extra biber # if biblatex used
sudo apt install texlive-science # algorithm2e, etc.
# Full installation (recommended)
brew install --cask mactex
# Minimal
brew install --cask basictex
sudo tlmgr update --self
sudo tlmgr install <package-name>
# If specific packages are missing
sudo tlmgr install <package-name>
Set up the correct compilation pipeline:
pdflatex main.tex
bibtex main
pdflatex main.tex
pdflatex main.tex
pdflatex main.tex
biber main
pdflatex main.tex
pdflatex main.tex
\bibliography{...} path is correctAfter configuration:
Produce:
Same-epoch comparison of training runs across wandb, neptune, tensorboard, or mlflow. Aligns runs at the student's current step (never current-vs-final-of-baseline) and separates proxy metrics from downstream targets. Use when the user asks to compare runs, check if a run is improving, track lag against a baseline, rank experiments, or evaluate run-vs-run performance.
Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list, dmesg, GPU stats, log scrollback, checkpoint state, then states a hypothesis as a hypothesis and runs a smoke before claiming a root cause. Use when the user asks why a run is failing, diverging, OOMing, hanging, slow, producing weird metrics, has crashed, or asks to debug, diagnose, troubleshoot, or investigate a training issue.
Pre-flight checklist for long-running ML training jobs covering config diff, run naming, path verification, monitoring setup, and restart-cleanup. Use when the user asks to launch, kick off, start, restart, or kill a training run, or mentions launching a multi-hour or multi-day GPU job (python train, accelerate launch, torchrun, deepspeed, sbatch, tmux training).
End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments. Handles missing or partial official code, missing training scripts, missing hyperparameters, and private datasets via similar-public-dataset substitution. Use when the user asks to reproduce, implement, replicate, or re-run a paper from scratch, or pastes an arxiv URL with reproduction intent.
Use when the user wants to analyze dataset bias, create stratified samples, evaluate fairness, or plan dataset collection. Triggers on phrases like "dataset bias", "stratified sample", "class imbalance", "data distribution", "fairness analysis", or "ethical review".
Use when the user wants to design experiments, plan ablation studies, structure baselines, or create incremental evaluation strategies. Triggers on phrases like "design ablation", "plan experiment", "what experiments should I run", "baseline comparison", or "experiment matrix".