Lab Practices
Find first-party documentation, repositories and engineering accounts.
- Anthropic (2)
- Openai (1)
- Google Deepmind (2)
- Xai (1)
- Meta (1)
- Chinese Labs (11)
- Other Labs (829)
847 resources · page 27 of 27
SEQUOR: A Multi-Turn Benchmark for Realistic Constraint Following
Creator not supplied; see original source.
arXiv paper (2026) introducing SEQUOR, a multi-turn benchmark for realistic constraint following.
SmolLM3 model card
Creator not supplied; see original source.
Hugging Face model card for SmolLM3-3B with architecture, training details and evaluation results.
Bielik v3 Small: Technical Report
Creator not supplied; see original source.
arXiv paper (2025) Bielik v3 Small technical report on SpeakLeash's small Polish language models.
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
Creator not supplied; see original source.
arXiv paper (2025) introducing Apertus, the Swiss AI Initiative's open and compliant multilingual LLMs.
T-Pro 2.1 instruction-following and tool-calling report
Creator not supplied; see original source.
T-Bank Habr article in Russian on T-Pro 2.1 improvements to instruction following and tool calling.
Connectionism (Thinking Machines Lab)
Creator not supplied; see original source.
Thinking Machines Lab blog Connectionism, with research posts on training, numerics and infrastructure experiments.
Pretraining Finnish ModernBERTs
Creator not supplied; see original source.
arXiv paper (2025) by TurkuNLP on pretraining Finnish ModernBERT encoder models.
UK AISI work
Creator not supplied; see original source.
UK AI Security Institute work page listing its research, evaluations and blog posts.
Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian
Creator not supplied; see original source.
arXiv paper (2024) introducing Vikhr, a family of open instruction-tuned Russian language models.
GLM-4.5 repo
by Zhipu / Z.ai
Inspect GLM release information and usage examples in the official repository.
DeepSeek open-infra-index
by DeepSeek
A directory of DeepSeek's published infrastructure components.
LAION blog
Creator not supplied; see original source.
LAION blog with posts on open datasets, models and research from the non-profit behind LAION-5B.
Meshy T2: Fast Native Mesh Generation with Flow Matching
Creator not supplied; see original source.
arXiv paper (2026) describing Meshy T2, fast native mesh generation with flow matching.
NVIDIA NeMo framework documentation
Creator not supplied; see original source.
NVIDIA NeMo Framework user guide: training and customising LLMs and multimodal models with parallelism and mixed precision.
Physical Intelligence blog
Creator not supplied; see original source.
Physical Intelligence blog with research posts on its π0 family of robot foundation models.