Open-source Valen: a visual decision model scoring candidates in 122–128 ms
aigclink · x · 2026-09-28
Valen extends System One decision-making to vision: it takes text, images or video and outputs probabilities over given candidate actions instead of generating tokens. Built on a Qwen3.5-0.8B/2B backbone with a shared decision head, it targets high-frequency agent reflexes like GUI popup detection, game movement and robot obstacle avoidance. Official numbers: 122–128 ms per decision, four parallel rounds in 1.24 s. The repo includes implementation, training and evaluation, with support for training on your own data.
Related event: Open-Source Visual Decision Model Valen Launches with 122ms Decisions(2 posts)→
More from coding & agent
- Fixing Claude Opus 5.5 long-context drift with an external SESSION_STATE.md protocol — socialwithaayan · 2026-09-28
- DeepLearning.AI launches spec-driven development course to make vibe coding reliable — ZabihullahAtal · 2026-09-28
- AI-made games are great only if you personally iterate on every detail down to the millisecond — IanArawjo · 2026-09-28
- cnakazawa: people are figuring out the best way to run the React Compiler — cnakazawa · 2026-09-28
- Google's Gemini Can Now Call Businesses for You on Pixel 11, Identifying Itself as AI — rvp · 2026-09-28
- IndicBankBench: 799-case benchmark shows banking AI assistants top out at 58.2% strict reliability — NPCI · 2026-09-28