✉news TechnologyRobotics first seen 1 d ago, last 19 h ago, peak #8
Kyutai Unveils REKI, a 2.4B-Parameter Model for Robot Manipulation
Original: Meet Kyutai REKI: The 2.4B VLA Model Bringing Efficient Memory to Robot Manipulation
AI research lab Kyutai has introduced REKI, a 2.4-billion-parameter vision-language-action model aimed at robot manipulation. The model's distinguishing feature is efficient memory use, allowing robots to perform manipulation tasks with lower computational overhead than larger VLA systems. Coverage so far is limited to a single technology publication, and details on benchmarks, availability, or real-world deployment have not yet been widely reported.
Why now: Tech audiences are interested in compact, efficient VLA models as an alternative to large, compute-heavy robotics AI systems.
Rank over time, top of the chart is #1. 4 snapshots from 23 h ago to 19 h ago.
Evidence
API: https://socialmediatrends-api.osmike.com/v1/trends/2657745