Menu
SkillsMP a collecté 14 skills depuis xiaden/ML-Experiments. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 14 skills collectés sur 14.
Methods for adaptive/token-budgeted visual generation — token merging, token pruning, early exiting, and self-budgeting tokenization in diffusion/image generation models.
Langue du texte source : anglais
Attention Residuals (AttnRes) implementation in the PDLI experiment. Covers AttnResDepth, AttnResBlock, and the L2RTP model that uses them. Essential for anyone modifying the transformer architecture or residual connections.
Langue du texte source : anglais
Comprehensive dependency maintenance — verifies import health, requirements.txt consistency, import hierarchy, and environment health.
Langue du texte source : anglais
Comprehensive paper library maintenance — cross-references papers.md against summaries, techniques, and PDFs. Detects orphans, missing registrations, and pulls missing papers.
Langue du texte source : anglais
Add a new research paper to the library — fetch the paper, write a structured summary to `docs/upstream/papers/`, implement its technique as a standalone Python module in `resources/techniques/`, and register it in `references/papers.md`.
Langue du texte source : anglais
Multi-scale/pyramidal approaches to denoising diffusion models. Covers the Ryu & Ye 2022 pyramidal DDPM paper and related coarse-to-fine diffusion architectures. Relevant to subdivision mode / spatial budget training and hierarchical latent backbones in the…
Langue du texte source : anglais
Comprehensive artifact maintenance — validates log naming, decision format, plan syntax compliance, staleness detection, and ensures the artifact corpus is parseable.
Langue du texte source : anglais
Dataset management maintenance — validates dataset integrity, version tracking, storage health, and cache consistency for training datasets.
Langue du texte source : anglais
GPU and VRAM health maintenance — validates CUDA availability, monitors VRAM usage, detects memory leaks, and ensures GPU readiness for training.
Langue du texte source : anglais
MLflow experiment tracking maintenance — validates run metadata, experiment organization, artifact consistency, and SQLite backend health.
Langue du texte source : anglais
Model checkpoint maintenance — validates .pt file integrity, metadata structure, version tracking, and storage health for trained disposition layers.
Langue du texte source : anglais
Validates standard/experimental notebook conventions, shared component usage, and lifecycle hooks. Provides grep-based checks and targeted auto-fix guidance.
Langue du texte source : anglais
Technique module maintenance — validates conventions, checks paper pulls, detects duplicates, verifies registration, and auto-fixes import issues.
Langue du texte source : anglais
Training pipeline maintenance — validates experiment runner, training loop, training rig, and component integration for all notebooks.
Langue du texte source : anglais