Beamr to Demonstrate Video Data Processing for Resilient AV Models at Smart Mobility Summit

Rhea-AI Summary

Beamr (NASDAQ:BMR) will showcase its ML-safe video data stack for autonomous vehicles at Smart Mobility Summit 2026, May 17–18 in Tel Aviv.

Beamr reports up to 50% file-size reduction with minimal ML accuracy impact, and depth-model tests showing smaller files plus reduced estimation error on vulnerable road users.

AI-generated analysis. Not financial advice.

Key Figures

File-size reduction vs baseline: 35.2% Depth error reduction on VRUs: 30.7% Aggregate depth error reduction: 16.0% +5 more

8 metrics

File-size reduction vs baseline 35.2% Depth Anything V2 trained on Beamr-compressed AV video

Depth error reduction on VRUs 30.7% Vulnerable road users (pedestrians, motorcyclists)

Aggregate depth error reduction 16.0% Across all object classes in AV model

File size reduction benchmark up to 50% ML-Safe benchmarks across AV pipeline with preserved detection

Model accuracy impact <2% Difference in ML model accuracy in ML-Safe benchmarks

Captioning file-size reduction 41%–57% World foundation model captioning workflow tests

Current share price $1.88 Pre-news close vs 52-week range $1.255–$4.3199

Market capitalization $30,283,215 Equity value prior to Smart Mobility Summit news

Market Reality Check

Price: $1.8800 Vol: Volume 77,603 vs 20-day a...

low vol

$1.8800 Last Close

Volume Volume 77,603 vs 20-day average 145,996 (relative volume 0.53x), indicating subdued pre-news trading. low

Technical Shares at $1.88, trading below the 200-day MA $2.25, reflecting a weak intermediate trend.

Peers on Argus

While BMR traded down 3.59%, two tracked peers in related tech (NTCL, AMOD) also...

2 Down

While BMR traded down 3.59%, two tracked peers in related tech (NTCL, AMOD) also appeared in momentum scans, each moving down with median change about -10.5%, suggesting broader pressure in the group.

Historical Context

5 past events · Latest: May 06 (Positive)

Pattern 5 events

Date	Event	Sentiment	Move	Catalyst
May 06	AI research update	Positive	-1.0%	CABR compression shown to improve AV depth estimation and cut data size.
Apr 20	Partner validation demo	Positive	+4.4%	dSPACE RTMaps integration validating ML-safe compression on AV data logs.
Apr 10	Product launch	Positive	+6.9%	Launch of VISTA platform for large-scale subjective video quality testing.
Mar 12	Conference demo	Positive	+1.8%	Planned ML-safe compression demo for physical AI at GTC 2026.
Feb 26	CEO letter & results	Neutral	-9.8%	CEO letter outlining AI video strategy and 2025 revenue, loss, and cash.

Pattern Detected

Product/AI validation news has often seen modestly positive reactions, while research-heavy or mixed financial updates have occasionally traded lower.

Recent Company History

Over the last few months, Beamr has repeatedly highlighted ML-safe compression and AI video workflows. Events on Apr 10 and Apr 20 showcased VISTA and dSPACE integrations, with positive price reactions of 6.9% and 4.37%. AI-focused demos at GTC on Mar 12 and the CABR research 6-K on May 6 saw smaller moves, including a -1.02% dip. The annual CEO letter on Feb 26 combined strategy and 2025 results and coincided with a -9.84% decline, showing sensitivity to financial disclosures versus purely technical news.

Market Pulse Summary

This announcement emphasizes Beamr’s ML-safe video data stack for autonomous vehicles, highlighting ...

Analysis

This announcement emphasizes Beamr’s ML-safe video data stack for autonomous vehicles, highlighting file-size reductions up to 50% and improved depth estimation accuracy, including a 30.7% error reduction on vulnerable road users. Recent history shows a steady cadence of AI and AV-focused demos and partnerships, alongside 2025 revenue of $3.09M and a net loss of $6.0M. Investors may watch for concrete deployment with AV customers, the impact on storage and networking costs, and future disclosures translating these benchmarks into revenue growth.

Key Terms

autonomous vehicles, monocular depth estimation, vulnerable road users, content-adaptive bitrate (cabr), +2 more

6 terms

autonomous vehicles technical

"ML-safe video data stack for autonomous vehicles (AV) at Smart Mobility Summit 2026"

Vehicles that use on-board sensors, cameras and software to navigate and drive without a human actively controlling them; think of them as robotic chauffeurs that can perceive roads, make decisions and follow traffic rules. For investors, they matter because they can reshape transportation costs, create new revenue streams (rides, logistics, software) and change regulatory and liability risks, so their adoption affects manufacturers, tech suppliers, insurers and transportation demand.

monocular depth estimation technical

"Depth Anything V2, a state-of-the-art monocular depth estimation model, was trained"

Monocular depth estimation is a computer vision technique that uses a single camera image to estimate how far away objects are, like judging distance from a photograph instead of using stereo eyes or sensors. For investors, it matters because the quality and cost of products that rely on cameras—such as autonomous vehicles, drones, robotics, augmented reality, and medical imaging—can be transformed by more accurate, cheaper depth sensing, affecting competitiveness, safety, and potential market adoption.

vulnerable road users technical

"reduction in depth estimation error on vulnerable road users (VRUs), including pedestrians"

People who are at higher risk of injury in traffic because they have little or no physical protection—examples include pedestrians, cyclists, scooter and motorcycle riders, children, the elderly and people with disabilities. Investors care because rules, safety standards, accident rates and public infrastructure that protect these road users can drive regulatory costs, liability exposure, insurance expenses and demand for safer vehicles or mobility services—similar to how weather affects insurance and construction planning.

content-adaptive bitrate (cabr) technical

"Beamr's Content-Adaptive Bitrate (CABR) technology analyzes each frame and adjusts"

Content-adaptive bitrate (CABR) is a video-delivery method that adjusts streaming quality in real time based on both the viewer’s network conditions and the complexity of what's on-screen, so simple scenes use less data while complex scenes get more detail. For investors, CABR matters because it can improve user experience and reduce bandwidth costs, which affects subscriber retention, platform scalability, and the economics of streaming services.

sdk technical

"CABR integrates into existing AV pipelines through SDK or FFmpeg plugin, runs on GPUs"

An SDK (software development kit) is a bundled set of tools, code samples and instructions that lets outside developers build software that works with a company’s platform or product. Think of it as a toolbox and recipe that makes it faster and easier for others to create compatible apps or services. For investors, an SDK matters because widespread developer use can boost product adoption, create new revenue streams and strengthen customer lock‑in, signaling potential future growth.

gpu technical

"FFmpeg plugin, runs on GPUs, ingests any input format, and outputs in industry-standard"

A GPU (graphics processing unit) is a specialized computer chip designed to handle many calculations at once, originally for rendering images and video but now widely used for tasks like artificial intelligence, data analysis and high-performance computing. Investors watch GPU demand and prices because strong sales often signal growth for chip makers and their customers, affect profit margins and capital spending, and can forecast wider trends in gaming, AI adoption and cloud services.

AI-generated analysis. Not financial advice.

Herzliya, Israel, May 12, 2026 (GLOBE NEWSWIRE) -- Beamr Imaging Ltd. (NASDAQ: BMR), a leader in video optimization technology and solutions, today announced that it will demonstrate its ML-safe video data stack for autonomous vehicles (AV) at Smart Mobility Summit 2026, held from May 17–18 at Expo Tel Aviv.

To meet with Beamr’s video experts (booth VT24), use this link

Beamr’s recent research shows how AV and machine vision teams can rely on compression as an asset that strengthens ML model resilience. The research extends Beamr’s video data stack, enabling AV teams to preserve ML accuracy with the advantages of reducing storage and networking costs across the model pipeline. In contrast, conventional compression methods force AV teams, managing tens to hundreds of petabytes of video data, into a trade-off between storage and networking efficiency and ML model integrity.

In Beamr's recent research, Depth Anything V2, a state-of-the-art monocular depth estimation model, was trained on video data compressed with Beamr's technology, which delivered 35.2% file-size reduction relative to baseline compression. The model demonstrated 30.7% reduction in depth estimation error on vulnerable road users (VRUs), including pedestrians and motorcyclists, and 16.0% aggregate reduction across all object classes.

This research extends Beamr’s ML-Safe benchmarks across the AV pipeline, which validated up to 50% file size reduction while preserving object detection with less than 2% difference in ML model accuracy. Testing for a world foundation model pipeline showed 41%–57% file size reduction with no measurable impact on captioning workflow outputs.

“AV and machine vision teams no longer have to carry the full cost of uncompressed data. Our AV video data stack adds significant robustness to the model and makes it ML-safe," said Beamr CEO, Sharon Carmel. "By using video data compressed with Beamr’s patented technology for training a depth model, we showcase that compression can become an enabler for machine vision models to perform better than models trained on uncompressed data.”

Beamr's Content-Adaptive Bitrate (CABR) technology analyzes each frame and adjusts compression to preserve the visual cues ML models depend on. CABR integrates into existing AV pipelines through SDK or FFmpeg plugin, runs on GPUs, ingests any input format, and outputs in industry-standard codecs - AVC, HEVC, and AV1.

To test Beamr’s technology on your own data, schedule a meeting at the summit (booth VT24) here

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

What will Beamr (NASDAQ:BMR) demonstrate at Smart Mobility Summit 2026?

Beamr will demonstrate its ML-safe video data stack for autonomous vehicles. According to Beamr, the stack lets AV teams reduce storage and networking costs while preserving machine learning accuracy across the model pipeline, using compression as a tool rather than a compromise.

How does Beamr's ML-safe video data stack benefit autonomous vehicle models (BMR)?

Beamr's video data stack aims to preserve AV model accuracy while cutting data size. According to Beamr, AV teams can avoid traditional trade-offs between storage efficiency and model integrity, improving resilience when managing tens to hundreds of petabytes of training video.

What results did Beamr report when training Depth Anything V2 with its compression technology?

Beamr reports that its compression cut Depth Anything V2 training video file size by 35.2% versus baseline. According to Beamr, the model showed 30.7% lower depth estimation error on vulnerable road users and 16.0% aggregate error reduction across all object classes.

What benchmarks has Beamr (BMR) shown for ML-safe compression across AV pipelines?

Beamr reports ML-Safe benchmarks with up to 50% file-size reduction while keeping object detection within 2% of baseline accuracy. According to Beamr, tests on a world foundation model pipeline showed 41%–57% file-size reduction without measurable impact on captioning workflow outputs.

How does Beamr's Content-Adaptive Bitrate (CABR) technology work in AV workflows?

Beamr's CABR analyzes each video frame and adjusts compression to preserve ML-relevant visual cues. According to Beamr, CABR integrates via SDK or FFmpeg plugin, runs on GPUs, accepts any input format, and outputs AVC, HEVC, or AV1 video for AV pipelines.

How can AV teams test Beamr's ML-safe video compression at Smart Mobility Summit 2026?

AV teams can test Beamr's technology by scheduling meetings at Smart Mobility Summit 2026. According to Beamr, its experts will be available at booth VT24, where attendees can discuss running Beamr's compression on their own autonomous driving video datasets.