LONDON--(BUSINESS WIRE)--Jan 14, 2026--
Ultralytics, the global leader in open-source vision AI, today announced the launch of Ultralytics YOLO26, the most advanced and deployable YOLO (You Only Look Once) model to date. Engineered from the ground up for edge and low-power devices, YOLO26 introduces a fully end-to-end, NMS-free architecture that fundamentally redefines how object detection is trained, deployed, and scaled in production, delivering industry-leading performance with dramatically reduced complexity.
This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20260114168538/en/
YOLO26 is built for demanding environments where efficiency, reliability, and hardware flexibility matter, including robotics, manufacturing automation, smart cities, logistics, healthcare, retail, and embedded AI.
Key architectural and training innovations in YOLO26 include:
Traditional object detection pipelines, built around fragile post-processing and GPU-heavy assumptions, are a hard blocker for real-world edge deployment. YOLO26 eliminates these constraints, enabling organizations to deploy state-of-the-art vision AI where it actually runs: on CPUs, edge accelerators, and embedded devices.
“YOLO26 is the fastest and most deployable object detection system available in the world today,” said Glenn Jocher, Founder and CEO of Ultralytics. “By removing entire stages of the inference pipeline, YOLO26 delivers state-of-the-art performance without the complexity that has held edge deployment back for years.”
Ultralytics YOLO26: Built for Real-World Edge Deployment
YOLO26 represents a shift toward native end-to-end object detection, producing predictions directly without post-processing steps such as NMS. This design significantly reduces latency, removes fragile post-processing steps, and shortens time-to-production by simplifying integration across cloud, edge, and embedded environments.
“YOLO26 represents a breakthrough in end-to-end object detection,” said Jing Qiu, Author of Ultralytics YOLO26 and Senior Machine Learning Engineer at Ultralytics. “By eliminating NMS and simplifying the model architecture, we achieve faster inference, stronger stability, and unmatched hardware portability, without sacrificing accuracy.”
A Unified Model Family Across Vision Tasks
YOLO26 is released as a multi-task model family, supporting object detection, instance segmentation, classification, pose estimation, and oriented object detection within a single, unified framework. Each model variant is designed to support training, validation, inference, and export, enabling teams to move from research to production faster and with fewer compromises.
“Ultralytics YOLO26 proves that world-class AI and real-world deployability no longer have to be a trade-off,” said Paula Derrenger, VP of Growth at Ultralytics. “This release removes the friction that has historically slowed down production vision AI, allowing teams to deploy faster, scale confidently, and standardize on a single best-in-class model family from cloud to edge.”
Ultralytics YOLOE-26: Open-Vocabulary Segmentation Models Built on YOLO26
Ultralytics is also introducing YOLOE-26, a new family of open-vocabulary segmentation models built on the latest YOLO26 architecture and training innovations.
YOLOE-26 is not a feature or a new task, but a specialized model family that reuses YOLO26’s end-to-end design to enable text prompts, visual prompts, and prompt-free segmentation. Available across all standard YOLO sizes, YOLOE-26 delivers stronger accuracy and more reliable real-world performance than previous open-vocabulary segmentation models, while integrating seamlessly into existing segmentation workflows.
Continuing the Open-Source Ultralytics YOLO Legacy
YOLO26 builds on Ultralytics’ long-standing commitment to open-source innovation. YOLO models are trusted by millions of developers worldwide and are used 2.5 billion times per day across industries and geographies. By continuously evolving YOLO with a focus on real-world constraints, Ultralytics enables organizations to deploy vision AI at scale, without sacrificing performance or transparency.
Through partnerships with innovators such as Axelera AI, Intel, DEEPX, and Sony AITRIOS, Ultralytics enables YOLO models to run efficiently on advanced AI hardware platforms. Together with a broad ecosystem of platform and hardware partners, Ultralytics continues its mission to deliver accessible, high-impact vision AI from cloud to edge.
YOLO26 will be available through the Ultralytics platform, with full support across training, inference, and export workflows. Enterprise licensing options are available for organizations deploying YOLO26 in commercial and closed environments, with support for production deployment, long-term maintenance, and scalable edge rollouts.
For more information and access to Ultralytics YOLO26, visit: platform.ultralytics.com/ultralytics/yolo26
About Ultralytics
Founded by Glenn Jocher, Ultralytics is the leading force in vision AI, best known for its Ultralytics YOLO (You Only Look Once) models. With 123,000 GitHub stars, 205+ million Python package downloads, and close to 2.5 billion daily usages, Ultralytics YOLOv5, YOLOv8, YOLO11, and now YOLO26 have become widely recognized object detection models globally.
Ultralytics empowers developers and enterprises with easy-to-use, high-performance vision AI technology. Its mission is to simplify and democratize AI, making it accessible and impactful across industries, including manufacturing, agriculture, healthcare, and logistics.
Ultralytics YOLO26 delivers edge-first vision AI
Boeing warned plane owners in 2011 about a broken part that contributed to a UPS plane crash that killed 15 last year but at that point the plane manufacturer didn't believe it threatened safety, the National Transportation Safety Board said Wednesday.
The UPS plane crashed in November 2025 shortly after taking off in Louisville, Kentucky, when the left engine flew off the wing as the plane rolled down the runway. Three pilots on the plane that was headed for Hawaii were killed along with 12 more people on the ground near Louisville’s Muhammad Ali International Airport.
The NTSB said Wednesday that Boeing had documented in 2011 there were four previous failures of a part that helps secure the MD-11's engines to the wings on three different planes, but at that point the plane manufacturer "determined it would not result in a safety of flight condition." These planes were actually built by McDonnell Douglas, which was later bought by Boeing.
The NTSB previously said investigators found cracks in some of the parts that held the engine to the wing. Those cracks hadn’t been caught in regular maintenance done on the plane, which raised questions about the adequacy of the maintenance schedule. The last time those key engine mount parts were examined closely was in October 2021, and the plane wasn’t due for another detailed inspection for roughly 7,000 more takeoffs and landings.
It’s not clear when the cracks started to develop in the parts that helped hold the engine on the wing, but this crash is reminiscent of a 1979 crash in Chicago when the left engine flew off an American Airlines DC-10 during takeoff, killing 273 people. The DC-10 was the predecessor of the MD-11.
That previous crash led to the worldwide grounding of 274 DC-10s. The airline workhorse was allowed to return to the skies because the NTSB determined that maintenance workers damaged the plane that crashed while improperly using a forklift to reattach the engine. That meant the crash wasn’t caused by a fatal design flaw even though there had already been a number of accidents involving DC-10s.
But former FAA and NTSB crash investigator Jeff Guzzetti said that a service bulletin McDonnell Douglas issued in 1980 did identify failures of the spherical bearing race as a “safety of flight condition” so it's surprising that Boeing didn't call it that in 2011. He said that American had removed the engine of that plane so it could inspect that bearing.
“I just think it raises questions regarding the adequacy of the severity of the 2011 service letter, and it also raises questions about how UPS incorporated that information and acted upon it,” Guzzetti said.
The service bulletin that Boeing issued didn't require plane owners to make repairs like an FAA airworthiness directive would, and the agency didn't issue such a directive.
Former federal crash investigator Alan Diehl said the notice from Boeing recommended replacing the bearings with a redesigned part that was less likely to fail, but it still allowed operators to replace defective bearings with another older bearing that had demonstrated it was prone to failing.
“As the investigation continues, the NTSB will have to address whether this service bulletin was an adequate solution to a known problem which could have had catastrophic results,” Diehl said. “The UPS crash highlights the need for increased maintenance measures on older airframes.”
NTSB didn't say whether there had been additional documented failures of the spherical bearing race since 2011. Investigators found that part broken into two pieces after the UPS crash, and the lugs that held that part were cracked.
Photos released by the NTSB of the Nov. 4 crash show flames erupting as the rear of the engine starting to detach before it flew up and over the wing. Then the wing was engulfed by fire as the burning engine flew above it.
The factual report released Wednesday doesn’t state what caused the engine to fly off, but it's clear that investigators are focused on the failure of this bearing. The ultimate conclusion won't come though until the NTSB's final report, which usually doesn't come until more than a year after a crash.
But the report will undoubtedly be cited in the first lawsuit over the crash that was filed last month and subsequent lawsuits.
The report does make clear that neither of the plane's two other engines were on fire before the crash. Some experts had previously speculated that debris flying off of the left engine might have damaged the engine on the tail.
Boeing, UPS and the Federal Aviation Administration are limited on what they can say while the NTSB investigation is ongoing, so they all declined to comment on Wednesday's report. Boeing and UPS both expressed condolences to the families that lost loved ones in the crash.
“We remain profoundly saddened by the Flight 2976 accident," UPS spokesperson Jim Mayer said. "Our thoughts continue to be with the families and Louisville community who are grieving, and we remain focused on the recovery effort,” Mayer said.
The 34-year-old MD-11 plane only got 30 feet (9.1 meters) off the ground before crashing into several industrial buildings just past the runway and generating a massive fireball that could be seen for miles. Dramatic videos of the crash showed the plane on fire as it plowed into buildings and released a massive plume of smoke.
Airlines quit flying this type of plane commercially years ago because it isn't as efficient as newer models, but they had continued to fly for cargo carriers like UPS and FedEx and a few of these planes were also modified for use in firefighting. All the MD-11s that had been in use and 10 related DC-10s have been grounded since the crash.
A cleanup crew detects and decontaminates water in a ditch during a tour of the UPS plane crash site, Tuesday, Jan. 13, 2026, in Louisville, Ky. (AP Photo/Jon Cherry)
Louisville Mayor Craig Greenberg speaks during a tour of the UPS plane crash site, Tuesday, Jan. 13, 2026, in Louisville, Ky. (AP Photo/Jon Cherry)
A UPS Boeing 737 takes over a destroyed truck during a tour of the UPS plane crash site, Tuesday, Jan. 13, 2026, in Louisville, Ky. (AP Photo/Jon Cherry)
FILE - This photo provided by the National Transportation Safety Board shows UPS plane crash scene on Thursday, Nov. 6, 2025 in Louisville, Ky. (NTSB via AP, File)
FILE - Plumes of smoke rise from the area of a UPS cargo plane crash at Louisville Muhammad Ali International Airport, on Tuesday, Nov. 4, 2025, in Louisville, Ky. (AP Photo/Jon Cherry, File)
