Beamr (BMR) and dSPACE show ML-safe AV video compression with 31% size cut Filing Impact Filing Sentiment Form Type 6-K Rhea-AI Filing Summary Beamr Imaging Ltd. filed a Form 6-K highlighting a joint demonstration with dSPACE that validates “ML-safe” video compression for autonomous vehicle data inside the dSPACE RTMaps ecosystem. Testing on real-world sequences showed Beamr’s Content-Adaptive Bitrate (CABR) compression delivered 31% file size reduction versus baseline encodes and 97% reduction versus uncompressed data while preserving machine learning model accuracy. The companies plan to extend ML-safe compression testing to additional stages such as video data simulation and hardware-in-the-loop testing. Beamr positions this capability as helping AV teams reduce data volumes and infrastructure demands without rebuilding existing RTMaps-based workflows. Positive - None. Negative - None. Key Figures File size reduction vs baseline: 31% reduction File size reduction vs uncompressed: 97% reduction Prior benchmark reduction: Up to 50% reduction +2 more 5 metrics File size reduction vs baseline 31% reduction CABR compression on real-world AV video sequences in dSPACE RTMaps File size reduction vs uncompressed 97% reduction CABR compression vs uncompressed AV video data Prior benchmark reduction Up to 50% reduction ML-safe video compression across AV pipeline in previous benchmarks Object detection accuracy change <2% difference in mAP Impact of CABR on object detection mean Average Precision Patents 53 patents Intellectual property backing Beamr’s CABR technology Key Terms ML-safe compression, Content-Adaptive Bitrate compression (CABR), RTMaps, hardware-in-the-loop (HIL) testing, +2 more 6 terms ML-safe compression technical "validating, for the first time, compression for autonomous vehicle (AV) video data ... while preserving machine learning (ML) model accuracy" ml-safe compression is a method of shrinking datasets or media so machine learning models can still read and learn from them without losing important signals or introducing bias. For investors, it matters because it can lower storage