AI · TECHNOLOGY · THE FUTURE
3 articles
Topic: vision-language models
NEWS AI Applications
Liquid AI's new 280M-parameter DSpark drafter guesses ahead so the LFM2.5-VL-3B vision model verifies instead of computing every token. All speedups are self-reported; here is how the technique works and where its gains stop.
NEWS Space & Aerospace / AI in Medicine
NVIDIA's new open model reads full 3D CT scans and narrates its reasoning step by step, like a radiologist thinking aloud. It scored best-in-class on a public benchmark and won praise from NIH radiologists, but it is a research foundation model, not a cleared diagnostic tool. Nothing about patient care changes today.
ANALYSIS Robotics
A new preprint tests vision-language reward models on 2,390 recorded real-robot trajectories and finds that equivalent instructions can produce contradictory judgments, revealing a measurable reliability gap before physical deployment.