xiaden/ML-Experiments

adaptive-token-budget

Methods for adaptive/token-budgeted visual generation — token merging, token pruning, early exiting, and self-budgeting tokenization in diffusion/image generation models.

원문 언어: 영어

attnres-implementation

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.

원문 언어: 영어

check-dependencies

Comprehensive dependency maintenance — verifies import health, requirements.txt consistency, import hierarchy, and environment health.

원문 언어: 영어

check-paper-library

Comprehensive paper library maintenance — cross-references papers.md against summaries, techniques, and PDFs. Detects orphans, missing registrations, and pulls missing papers.

원문 언어: 영어

add-research-paper

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`.

원문 언어: 영어

pyramidal-diffusion

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…

원문 언어: 영어

validate-artifacts

Comprehensive artifact maintenance — validates log naming, decision format, plan syntax compliance, staleness detection, and ensures the artifact corpus is parseable.

원문 언어: 영어

validate-datasets

Dataset management maintenance — validates dataset integrity, version tracking, storage health, and cache consistency for training datasets.

원문 언어: 영어

validate-gpu-health

GPU and VRAM health maintenance — validates CUDA availability, monitors VRAM usage, detects memory leaks, and ensures GPU readiness for training.

원문 언어: 영어

validate-mlflow

MLflow experiment tracking maintenance — validates run metadata, experiment organization, artifact consistency, and SQLite backend health.

원문 언어: 영어

validate-model-artifacts

Model checkpoint maintenance — validates .pt file integrity, metadata structure, version tracking, and storage health for trained disposition layers.

원문 언어: 영어

validate-notebooks

Validates standard/experimental notebook conventions, shared component usage, and lifecycle hooks. Provides grep-based checks and targeted auto-fix guidance.

원문 언어: 영어

validate-techniques

Technique module maintenance — validates conventions, checks paper pulls, detects duplicates, verifies registration, and auto-fixes import issues.

원문 언어: 영어

validate-training-pipeline

Training pipeline maintenance — validates experiment runner, training loop, training rig, and component integration for all notebooks.

원문 언어: 영어