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.

لغة النص الأصلي: الإنجليزية

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.

لغة النص الأصلي: الإنجليزية

check-dependencies

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

لغة النص الأصلي: الإنجليزية

check-paper-library

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

لغة النص الأصلي: الإنجليزية

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`.

لغة النص الأصلي: الإنجليزية

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…

لغة النص الأصلي: الإنجليزية

validate-artifacts

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

لغة النص الأصلي: الإنجليزية

validate-datasets

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

لغة النص الأصلي: الإنجليزية

validate-gpu-health

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

لغة النص الأصلي: الإنجليزية

validate-mlflow

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

لغة النص الأصلي: الإنجليزية

validate-model-artifacts

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

لغة النص الأصلي: الإنجليزية

validate-notebooks

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

لغة النص الأصلي: الإنجليزية

validate-techniques

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

لغة النص الأصلي: الإنجليزية

validate-training-pipeline

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

لغة النص الأصلي: الإنجليزية