Beamr Validates ML-Safe Compression for dSPACE Data Logging

Beamr (NASDAQ: BMR) and dSPACE validated ML-safe video compression inside the dSPACE RTMaps ecosystem, demonstrating 31% file size reduction vs baseline encodes and 97% reduction vs uncompressed data while preserving ML model accuracy.

Rhea-AI Summary

Beamr (NASDAQ: BMR) and dSPACE validated ML-safe video compression inside the dSPACE RTMaps ecosystem, demonstrating 31% file size reduction vs baseline encodes and 97% reduction vs uncompressed data while preserving ML model accuracy.

The joint demonstration will be presented at the dSPACE User Conference, April 21-22, 2026, in Novi, Michigan, and showed object-detection impact of <2% mean Average Precision difference and no measurable effect on AV captioning embeddings.

Positive

• 31% file size reduction vs baseline encodes
• 97% file size reduction vs uncompressed data
• <2% difference in mean Average Precision for object detection
• Validated inside dSPACE RTMaps multisensor data-logging framework
• Planned extension to simulation and HIL stages

Negative

• None.

Argus Apr 20 session

+4.37% close to close Open Argus

Details

News Market Reaction – BMR

In the Apr 20 session, BMR gained 4.37%, reflecting a moderate positive market reaction.

Data tracked by StockTitan Argus on the day of publication.

Market Context

This announcement highlights further validation of Beamr’s ML-safe CABR compression, showing 31% and...

Analysis

This announcement highlights further validation of Beamr’s ML-safe CABR compression, showing 31% and 97% file size reductions in the dSPACE RTMaps ecosystem while preserving model accuracy. It extends a pattern of product and partner-focused updates around AI video workflows. Investors may watch for concrete deployment metrics, revenue contributions, and follow-on collaborations stemming from this validation, especially as the shares previously traded below the $2.36 200-day moving average and well under the 52-week high before the news.

Key Figures

File size reduction vs baseline: 31% File size reduction vs uncompressed: 97% Prior CABR reduction: 50% +2 more

File size reduction vs baseline

31%

Compression on footage from dSPACE RTMaps compared to baseline encodes

File size reduction vs uncompressed

97%

Compression of previously uncompressed AV data while preserving ML accuracy

Prior CABR reduction

50%

Earlier CABR benchmarks for ML-safe compression across AV pipeline

Object detection mAP change

<2%

Difference in mean Average Precision for object detection tasks with CABR

Embedding models used

2 models

Number of embedding models used to evaluate AV captioning impact

Historical Context

5 past events · Latest: Apr 10

5 events

1. Apr 10

   Product launch

   24h Move

   +6.9%

   Launch of VISTA platform for large-scale subjective video quality testing.

2. Mar 12

   Tech demonstration

   24h Move

   +1.8%

   Planned demo of ML-safe video compression for physical AI at GTC 2026.

3. Feb 26

   CEO letter, results

   24h Move

   -9.8%

   Annual CEO letter summarizing AI video progress and 2025 financial results.

4. Feb 25

   Contract renewal

   24h Move

   +9.1%

   Renewal of large-scale streaming contract with JioHotstar using CABR.

5. Jan 28

   Tech showcase

   24h Move

   +4.2%

   Showcase of NVIDIA-powered validation framework for AI-enhanced and compressed video.

24h Move is the share-price change in the day after each event; other market factors may also have contributed.

Key Terms

machine learning, ml-safe compression, autonomous vehicle, mean average precision, +2 more

6 terms

machine learning technical

"while preserving machine learning (ML) model accuracy."

Machine learning is a set of computer programs that learn patterns from large amounts of data and improve their predictions or decisions over time, like a recipe that gets better each time it’s adjusted based on taste tests. For investors it matters because these systems can speed up analysis, spot trends or risks humans might miss, automate routine work, and potentially create competitive advantages or cost savings that affect a company’s performance.

View in glossary

ml-safe compression technical

"Beamr Validates ML-Safe Compression for dSPACE Data Logging"

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 and bandwidth costs, speed model deployment, and reduce regulatory or operational risk by preserving model accuracy and fairness—think of compressing a photo but keeping the faces clear so automated recognition still works.

autonomous vehicle technical

"compression for autonomous vehicle (AV) video data in the dSPACE RTMaps ecosystem"

A vehicle that can navigate and operate without a person actively controlling the steering, braking and acceleration, using onboard sensors, cameras, maps and software to make driving decisions much like a robot chauffeur. Investors watch autonomous vehicles because they can reshape transportation economics—lowering labor and operating costs for fleets, creating new service and data revenues, and introducing regulatory and liability risks that can rapidly change a company's value, similar to how smartphones transformed multiple industries.

mean average precision technical

"For object detection tasks, CABR showed <2% difference in mean Average Precision"

Mean average precision is a single-number measure used to judge how well a ranking or recommendation system orders relevant items near the top; it averages precision scores at each point a correct item appears and then takes the mean across multiple queries. For investors, it matters when assessing tools that sort news, signals, or trade ideas — higher values mean the system more reliably surfaces the most important items first, like a well-organized playlist that puts your favorite songs at the top.

embedding models technical

"evaluated using two embedding models."

Embedding models are machine learning tools that convert text, images or other data into compact lists of numbers that capture meaning and relationships, like assigning coordinates on a map so similar items sit near each other. For investors, they power smarter search, faster document review, automated news and sentiment analysis, and better recommendation or fraud detection systems, which can cut costs and speed decisions. Their use can influence a company’s efficiency, product strength and competitive edge.

hardware-in-the-loop (hil) technical

"including video data simulation and hardware-in-the-loop (HIL) testing."

Hardware-in-the-loop (HIL) is a testing method where real physical components are connected to a computer simulation that mimics the rest of the system in real time, like putting an actual car brake into a driving simulator. It matters to investors because HIL shortens development time, uncovers design flaws before costly production, and improves product reliability—factors that can lower costs, reduce recall risk and speed time-to-market.

AI-generated analysis. How Rhea-AI works. Not financial advice.

See more from StockTitan in Google Search and AI answers. Adds StockTitan as a preferred source · opens Google

Add on Google Not now

Beamr delivered 31% file size reduction compared to baseline encodes on footage from dSPACE RTMaps. Results to be demonstrated at dSPACE User Conference, April 21-22, Novi, Michigan

Herzliya, Israel, April 20, 2026 (GLOBE NEWSWIRE) -- Beamr Imaging Ltd. (NASDAQ: BMR), a leader in video optimization technology and solutions, and dSPACE, a leading provider of solutions for the development of connected, autonomous, and electrically powered vehicles, today announced a joint demonstration validating, for the first time, compression for autonomous vehicle (AV) video data in the dSPACE RTMaps ecosystem while preserving machine learning (ML) model accuracy. The demonstration will be presented at dSPACE user conference, held from April 21-22 in Novi, Michigan.

AV fleets generate massive volumes of multi-camera video data during test drives. A single run produces terabytes of footage, choking storage, slowing data transfer, and extending development iteration cycles. Applying compression at the data logging stage reduces the volume of video data entering downstream storage and processing pipelines, where infrastructure costs accumulate at scale. Yet many AV teams hesitate to compress, lacking confidence that file size reduction can be achieved without compromising ML model accuracy.

Testing on real-world sequences processed through dSPACE RTMaps showed Beamr Content-Adaptive Bitrate compression (CABR) delivered 31% file size reduction compared to baseline encodes, and 97% reduction for uncompressed data - while preserving ML model accuracy. RTMaps is a multisensor software framework for data logging and replay, software development, and real-time execution.

In previous benchmarks, CABR demonstrated ML-safe video data compression with up to 50% file size reduction for real-world and synthetic video data, across the AV pipeline. For object detection tasks, CABR showed <2% difference in mean Average Precision, well within the model’s expected variance. Testing with world foundation models showed no measurable impact on AV captioning, evaluated using two embedding models. Beamr and dSPACE plan to extend ML-safe compression testing to additional stages, including video data simulation and hardware-in-the-loop (HIL) testing.

“ML-safe compression is essential for any team running AV pipelines at scale,” said Dani Megrelishvili, Beamr Chief Product Officer. “Validating Beamr's technology inside RTMaps brings that assurance into the dSPACE ecosystem, so teams already running these workflows can reduce their data volumes without rebuilding their pipeline."

To schedule a meeting at dSPACE user conference, please use this link.

About Beamr

Beamr (Nasdaq: BMR) is a world leader in content-adaptive video compression, trusted by top media companies including Netflix and Paramount. Beamr’s perceptual optimization technology (CABR) is backed by 53 patents and a winner of Emmy® Award for Technology and Engineering. The innovative technology reduces video file sizes by up to 50% while preserving quality and enabling AI- powered enhancements.

Beamr powers efficient video workflows across high-growth markets, such as media and entertainment, user-generated content, machine learning, and autonomous vehicles. Its flexible deployment options include on-premises, private or public cloud, with convenient availability for Amazon Web Services (AWS) and Oracle Cloud Infrastructure (OCI) customers.

For more details, please visit www.beamr.com or the investors’ website www.investors.beamr.com

Forward-Looking Statements

This press release contains “forward-looking statements” that are subject to substantial risks and uncertainties. Forward-looking statements in this communication may include, among other things, statements about Beamr’s strategic and business plans, technology, relationships, objectives and expectations for its business, the impact of trends on and interest in its business, intellectual property or product and its future results, operations and financial performance and condition. All statements, other than statements of historical fact, contained in this press release are forward-looking statements. Forward- looking statements contained in this press release may be identified by the use of words such as “anticipate,” “believe,” “contemplate,” “could,” “estimate,” “expect,” “intend,” “seek,” “may,” “might,” “plan,” “potential,” “predict,” “project,” “target,” “aim,” “should,” “will” “would,” or the negative of these words or other similar expressions, although not all forward-looking statements contain these words. Forward-looking statements are based on the Company’s current expectations and are subject to inherent uncertainties, risks and assumptions that are difficult to predict. Further, certain forward-looking statements are based on assumptions as to future events that may not prove to be accurate. For a more detailed description of the risks and uncertainties affecting the Company, reference is made to the Company’s reports filed from time to time with the Securities and Exchange Commission (“SEC”), including, but not limited to, the risks detailed in the Company’s annual report filed with the SEC on February 26, 2026 and in subsequent filings with the SEC. Forward-looking statements contained in this announcement are made as of the date hereof and the Company undertakes no duty to update such information except as required under applicable law.

Investor Contact
investorrelations@beamr.com

FAQ

AI-generated questions and answers. How Rhea-AI works. Not financial advice.

How much file size reduction did Beamr report for dSPACE RTMaps footage (BMR) on April 20, 2026?

Beamr reported a 31% file size reduction versus baseline encodes for RTMaps footage. According to the company, testing also showed a 97% reduction compared with uncompressed data while maintaining ML accuracy.

Did Beamr's compression affect ML model accuracy in the dSPACE RTMaps tests (BMR)?

No significant accuracy loss was reported; object detection showed <2% mean Average Precision difference. According to the company, that change is within the model’s expected variance and is considered ML-safe for tested tasks.

Where and when will Beamr and dSPACE present the ML-safe compression results (BMR)?

The joint demonstration will be presented at the dSPACE User Conference on April 21-22, 2026 in Novi, Michigan. According to the company, attendees can view results and discuss integration into RTMaps workflows there.

Which AV data workflows did Beamr validate ML-safe compression for within dSPACE RTMaps (BMR)?

Beamr validated compression for data logging and replay workflows inside RTMaps, preserving downstream ML tasks. According to the company, tests included object detection and AV captioning evaluated with two embedding models.

Will Beamr and dSPACE expand ML-safe compression testing beyond RTMaps (BMR)?

Yes. According to the company, Beamr and dSPACE plan to extend testing to additional stages, including video data simulation and hardware-in-the-loop (HIL) testing to cover broader AV pipeline use cases.