README / README.md
shadowlilac's picture
Update README.md
bc80518 verified
|
Raw
History Blame Contribute Delete
929 Bytes
metadata
title: README
emoji: 🚀
colorFrom: gray
colorTo: indigo
sdk: static
pinned: false

System-L Research

LLM pre-training, mid-training, and RL research, active since 2024, led by ShadOwO (previously known as ShadowLilac)

Focus: AI anime girl characters and streaming-optimized model development.


Research areas

  • Continued pretraining around teaching LLMs VTuber/streamer/VRChat specific knowledge
  • Reward models for character consistency and preference scoring
  • Long-horizon RL around teaching LLMs to be first-person agents in videogames
  • High quality low latency voice generation

Compute resources

The lab has access to the following compute resources. Additional compute is acquired via Lambda Cloud

  • Nvidia GB10 (2x)
  • i7-13700F, RTX 3090 (2x), 128gb RAM, 4TB
  • 8TB Disk

Models, datasets, and research artifacts published here are part of ongoing work in character-driven LLM development.