distillation

Yzmblog/DMAD

+37

DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation

pocket-tank

+29

A 14M-parameter LLM keeps a virtual fish tank alive on an $8 ESP32-S3 — distilled from a 26B teacher into 7.56 MB, no network.

FastVideo

+30

A unified inference and post-training framework for accelerated video generation.

reasoning-from-scratch

+35

Implement a reasoning LLM in PyTorch from scratch, step by step

lightly-train

+15

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

TurboDiffusion

+4

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

auto

+1

the agi compiler: records llm agent behavior, proves what repeats, and compiles it into verified, sandboxed wasm binaries that run for microdollars. nothing figured out twice, paper: https://arxiv.org/abs/2607.04542

awesome-knowledge-distillation

+1

Awesome Knowledge Distillation