diloco:
  type: article
  title: "DiLoCo: Distributed Low-Communication Training of Language Models"
  author: ["Douillard, Arthur"]
  date: 2023
  url: https://arxiv.org/abs/2311.08105
mdlm:
  type: article
  title: Simple and Effective Masked Diffusion Language Models
  author: ["Sahoo, Subham Sekhar"]
  date: 2024
  url: https://arxiv.org/abs/2406.07524
smdm:
  type: article
  title: Scaling up Masked Diffusion Models on Text
  author: ["Nie, Shen"]
  date: 2025
  url: https://arxiv.org/abs/2410.18514
llada:
  type: article
  title: Large Language Diffusion Models
  author: ["Nie, Shen"]
  date: 2025
  url: https://arxiv.org/abs/2502.09992
ultrafineweb:
  type: article
  title: "Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Data"
  author: ["Wang, Yudong"]
  date: 2025
  url: https://arxiv.org/abs/2505.05427
olmo3:
  type: web
  title: "OLMo 3 stage-2 mid-training mix (dolma3_dolmino_mix-100B-1125)"
  author: ["Team OLMo"]
  date: 2025
  url: https://huggingface.co/datasets/allenai/dolma3_dolmino_mix-100B-1125
d2z:
  type: article
  title: "Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs"
  author: ["Bergsma, Shane"]
  date: 2025
  url: https://arxiv.org/abs/2502.15938
muon:
  type: web
  title: "Muon: An optimizer for hidden layers in neural networks"
  author: ["Jordan, Keller"]
  date: 2024
  url: https://kellerjordan.github.io/posts/muon/
moonlight:
  type: article
  title: Muon is Scalable for LLM Training
  author: ["Liu, Jingyuan"]
  date: 2025
  url: https://arxiv.org/abs/2502.16982
cautious:
  type: article
  title: "Cautious Optimizers: Improving Training with One Line of Code"
  author: ["Liang, Kaizhao"]
  date: 2024
  url: https://arxiv.org/abs/2411.16085
lmeval:
  type: web
  title: A framework for few-shot language model evaluation (lm-evaluation-harness)
  author: ["Gao, Leo"]
  date: 2024
  url: https://github.com/EleutherAI/lm-evaluation-harness
pythia:
  type: article
  title: "Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling"
  author: ["Biderman, Stella"]
  date: 2023
  url: https://arxiv.org/abs/2304.01373
smollm2:
  type: article
  title: "SmolLM2: When Smol Goes Big - Data-Centric Training of a Small Language Model"
  author: ["Ben Allal, Loubna"]
  date: 2025
  url: https://arxiv.org/abs/2502.02737
qwen25:
  type: article
  title: Qwen2.5 Technical Report
  author: ["Qwen Team"]
  date: 2024
  url: https://arxiv.org/abs/2412.15115