view article Article Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries +7 Mar 10 • 131
BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs Paper • 2604.02045 • Published 20 days ago • 33
BidirLM-Embedding Collection BidirLM is a family of 5 frontier bidirectional encoders, including an omnimodal variant at 2.5B. • 6 items • Updated 15 days ago • 5
view article Article How we OCR'ed 30,000 papers using Codex, open OCR models and Jobs 15 days ago • 58
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 20 days ago • 873
view article Article Introducing Cohere-transcribe: state-of-the-art speech recognition 27 days ago • 40
MolmoWeb-Data Collection This is the collection of all datasets in MolmoWebMix. • 6 items • Updated 29 days ago • 26
GLiNER-relex Collection Zero-shot joint NER and relation extraction models • 4 items • Updated Mar 19 • 2
Mistral Small 4 Collection A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated Mar 16 • 67