Olmo Hybrid lands at COLM with a 7B open transformer-RNN design
SonglinYang4 · x · 2026-07-21
Allen AI’s Olmo Hybrid has been accepted to COLM.
The model is a 7B fully open system that combines transformer and linear RNN layers. The team says it clearly beats Olmo 3 7B on evaluations, and pairs the release with new theory and scaling experiments explaining why the hybrid design works.
More from Research
- Project APE finds verifier reliability drops when papers contain multiple errors — soumitrashukla9 · 2026-07-22
- Project APE says verifier costs fell about 90x in a year as Chinese open models lead — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22
- Project APE builds its verifier benchmark from 100 AI-written papers with injected errors — soumitrashukla9 · 2026-07-22
- Paper proposes a CRED taxonomy and benchmark to measure research-error detectors — soumitrashukla9 · 2026-07-22
- OpenAI says long-horizon models need safety and alignment checks across full action sequences — rhiever · 2026-07-22