Foundation models & labs for advanced learners
684 resources · page 21 of 22
DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters
by Peter Schneider-Kamp et al. (University of Southern Denmark)
arXiv paper (2026) describing DFM Mimir v1, a 1B-parameter Danish open model.
DeepSeek-V3 Technical Report
by DeepSeek-AI
arXiv paper (2024) DeepSeek-V3 Technical Report: MLA attention, DeepSeekMoE and FP8 training.
deepset (German’s Next Language Model)
by Branden Chan et al. (deepset)
arXiv HTML version of deepset's German's Next Language Model paper (2020) on GBERT and GELECTRA.
Eval awareness in Claude Opus 4.6's BrowseComp performance
by Anthropic
Anthropic engineering post on Claude Opus 4.6 showing evaluation awareness on the BrowseComp benchmark.
ÚFAL at MultiLexNorm 2021: Improving Multilingual Lexical Normalization by Fine-tuning ByT5
by David Samuel and Milan Straka (ÚFAL, Charles University)
arXiv paper (2021) describing ÚFAL's system for multilingual lexical normalisation at MultiLexNorm 2021.
GLM-4.5 ARC tech report
arXiv paper (2025) GLM-4.5 technical report on Z.ai's agentic, reasoning and coding foundation models.
Google DeepMind Publications
Google DeepMind publications index: research papers across AI and science.
Latxa: An Open Language Model and Evaluation Suite for Basque
by Julen Etxaniz et al. (University of the Basque Country)
arXiv paper (2024) introducing Latxa, an open Basque language model and evaluation suite.
Meltemi: The first open Large Language Model for Greek
by Leon Voukoutis et al. (ILSP, Athena Research Center)
arXiv paper (2024) introducing Meltemi, an open large language model for Greek.
Mitigating Catastrophic Forgetting in Language Transfer via Model Merging
by Anton Alexandrov et al. (INSAIT)
EMNLP 2024 Findings paper (INSAIT) on reducing catastrophic forgetting in language transfer via Branch-and-Merge model merging.
GePpeTto Carves Italian into a Language Model
by Lorenzo De Mattei et al. (ItaliaNLP Lab, ILC-CNR)
CEUR-WS paper (PDF) presenting GePpeTto, an Italian GPT-2 language model.
jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
by Michael Günther et al. (Jina AI)
arXiv paper (2025) introducing jina-embeddings-v4, universal multimodal multilingual embeddings.
Swedish Whispers: Leveraging a Massive Speech Corpus for Swedish Speech Recognition
by Leonora Vesterbacka et al. (National Library of Sweden)
arXiv paper (2025) by KBLab on Swedish Whisper models trained on a large Swedish speech corpus.
Kimi K3: Open Frontier Intelligence
arXiv paper (2026) Kimi K3 technical report from Moonshot AI.
Kling-Omni Technical Report
arXiv HTML version of the Kling-Omni technical report (2025) on Kuaishou's video model architecture and training.
LAION-5B: An open large-scale dataset for training next generation image-text models
by Christoph Schuhmann et al. (LAION)
arXiv paper (2022) introducing LAION-5B, an open dataset of 5.85 billion image-text pairs.
LoRA Without Regret
Thinking Machines Lab post LoRA Without Regret: when LoRA matches full fine-tuning, with hyperparameter guidance.
Luma Unified Models (Uni-1)
by Luma AI
Luma AI Uni-1 page: multimodal reasoning model that generates images.
MERA paper
by Alena Fenogenova et al. (SberDevices)
arXiv paper (2024) introducing MERA, a benchmark for evaluating LLMs in Russian.
MiniMax-M1 paper
by MiniMax
arXiv paper (2025) describing MiniMax-M1, scaling test-time compute with lightning attention.
MiniMax Sparse Attention
by Xunhao Lai et al. (Peking University)
arXiv paper (2026) describing MiniMax Sparse Attention, the attention design accompanying MiniMax-M3.
Mistral AI Research
by Mistral AI
Mistral AI research page listing papers and technical reports on its language, speech, document and robotics models.
Muon is Scalable for LLM Training (Moonlight)
by Jingyuan Liu et al. (Moonshot AI)
arXiv paper (2025) by Moonshot AI showing the Muon optimizer scales to LLM training, with the Moonlight model.
Annotation-Efficient Vision-Language Model Adaptation to the Polish Language Using the LLaVA Framework
by Grzegorz Statkiewicz et al. (NASK National Research Institute)
arXiv paper (2026) by NASK on annotation-efficient adaptation of vision-language models to Polish.
CLOVA Tech Blog
NAVER CLOVA tech blog with technical posts on HyperCLOVA X models and their serving.
NorwAI's Large Language Models: Technical Report
by Jon Atle Gulla et al. (NTNU)
arXiv paper (2026) technical report on NorwAI's Norwegian large language models.
Nous Research blog
Nous Research blog with posts on Hermes models, the Psyche training network and research.
GlórIA: A Generative and Open Large Language Model for Portuguese
by Ricardo Lopes et al. (NOVA LINCS, NOVA University Lisbon)
arXiv paper (2024) introducing GlórIA, an open generative language model for European Portuguese.
OpenLLM-Ro: Technical Report on Open-source Romanian LLMs
by Mihai Masala et al. (National University of Science and Technology POLITEHNICA Bucharest)
arXiv paper (2024) technical report on OpenLLM-Ro, open-source Romanian LLMs.
Preferred Networks 日本語 technology blog
Preferred Networks Japanese tech blog with research and engineering writeups by its staff.
Prime Intellect blog
Prime Intellect blog with posts on decentralised training, INTELLECT models and its Environments Hub.
Qwen3 Technical Report
by An Yang et al. (Qwen Team, Alibaba)
arXiv paper (2025) Qwen3 Technical Report describing the Qwen3 model family, architecture and training.