News

Two western Pennsylvania companies — Kate’s Real Food and Healthy Origins — are expanding beyond the U.S. through a partnership with Coupang.

Coupang, a U.S.-technology and Fortune 150 company, operates one of the largest e-commerce platforms in South Korea. It allows American sellers to reach customers overseas without setting up their own distribution networks. Businesses ship products to a domestic Coupang logistics facility. From there, the company manages storage, fulfillment and delivery directly to customers abroad.

For Kate’s Real Food and Healthy Origins, this system opens the door to new markets without requiring on-the-ground operations. Kate’s Real Food makes organic energy and protein bars. Healthy Origins is a family-owned supplements business based near Pittsburgh. Both are now selling to customers in South Korea and in Healthy Origins’ case, Taiwan as well.

That structure addresses a practical gap for growing brands: how to access international demand without building international operations. Instead of navigating foreign warehousing and retail partnerships independently, sellers plug into an existing marketplace and logistics system.

“At Coupang, we’re proud to help thousands of American small and medium-sized businesses, agricultural producers and larger brands sell their goods to customers around the world”, said Coupang vice president Bill Anaya. “We’ve built an innovative, AI-driven export engine that enables great American entrepreneurs — like those who created Kate’s Real Food and Healthy Origins — to expand their horizons, find new revenue abroad and keep growing their local teams".

For Kate’s Real Food, the move marks its entry into South Korea for the first time. For Healthy Origins, the results have been measurable. The company reports that sales of its products on the platform have increased more than 50% year over year since partnering with Coupang. It has also expanded into Taiwan.

“Partnering with Coupang has been a significant step forward for our business”, said Bret Eby, CEO of Healthy Origins. “Coupang makes it easier to deliver a great shopping experience and we’ve appreciated the collaboration and support throughout the process. Its scale, efficiency and consumer reach in Korea are unmatched and launching on Coupang allowed us to elevate our presence and connect with customers in a much more impactful and direct way”.

The broader relevance lies in the model itself. Digital marketplaces are building integrated cross-border infrastructure. That shift changes what international expansion requires. Smaller regional brands no longer need to replicate warehousing, logistics and retail partnerships in every new market. Instead, they can plug into an existing system and reach customers abroad.

In this case, two Pennsylvania companies are doing exactly that. Their expansion illustrates how platform-led trade is reshaping the path from local operations to global reach.

The Knot Worldwide, a global wedding technology platform and vendor marketplace, has launched a new grant initiative aimed at small businesses in the wedding industry.

The company, which operates brands such as The Knot and WeddingWire, connects couples with wedding professionals and provides tools to help vendors grow. It says the new WeddingPro Grant Program is designed to address a persistent challenge in the sector: access to capital.

Under the program, up to US$500,000 will be distributed to U.S.-based wedding professionals who run small businesses. The support will come in the form of financial grants, advertising credits on WeddingPro and mentorship. Selected businesses will also receive access to education resources and community support through the company’s network.

The move comes at a time when many wedding businesses remain small and resource-constrained. According to the company’s State of the Vendor Report, more than half of wedding businesses employ fewer than ten people. Three in four professionals surveyed said adaptability is critical to long-term success, while flexible funding remains a barrier. The grant program is positioned as a response to that funding gap.

“Our mission at The Knot Worldwide is to help the nearly 900,000 small businesses on our global platforms get discovered through our centralized vendor marketplace as well as give them the tools and resources to grow their business,” said Raina Moskowitz, Chief Executive Officer, The Knot Worldwide. “We consistently hear from our wedding professionals that access to capital is a barrier to getting started in the industry. With our new WeddingPro Grant Program, we will provide access to both capital and critical support services such as mentorship and education that will enable small business owners to further grow and scale.”

The application window opens on February 23 and closes on March 27. Winners are expected to be notified by May 2026, subject to eligibility verification and compliance with the official rules.

The program is open to U.S. wedding professionals who operate small businesses, have been in business for at least six months, can demonstrate an active revenue stream and earn at least 50% of their revenue from weddings. Applicants must submit a short form and a video outlining their business and how they would use the grant funds over the next 12 to 24 months. They can choose whether they prefer a monetary grant or free advertising support on WeddingPro.

To execute the program, The Knot Worldwide has partnered with the Global Entrepreneurship Network, which works with entrepreneurs worldwide. The company says the initiative builds on earlier efforts to support vendors on its platform, which includes about 200,000 wedding professionals in the United States. Its impact will depend on how effectively the support reaches the businesses that need it most. The real measure will be whether it helps them achieve steady, sustainable growth.

As AI tools improve, creating 3D content is becoming faster and easier. However, building that content into interactive experiences still requires time, structure and technical work. That difference between generation and execution is where HTC VIVERSE and World Labs are focusing their new collaboration.

HTC VIVERSE is a 3D content platform developed by HTC. It provides creators with tools to build, refine and publish interactive virtual environments. Meanwhile, World Labs is an AI startup founded by researcher Fei-Fei Li and a team of machine learning specialists. The company recently introduced Marble, a tool that generates full 3D environments from simple text, image or video prompts.

While Marble can quickly create a digital world, that world on its own is not yet a finished experience. It still needs structure, navigation and interaction. This is where VIVERSE fits in. By combining Marble’s world generation with VIVERSE’s building tools, creators can move from an AI-generated scene to a usable, interactive product.

In practice, the workflow works in two steps. First, Marble produces the base 3D environment. Then, creators bring that environment into VIVERSE, where they add game mechanics, scenes and interactive elements. In this model, AI handles the early visual creation, while the human creator defines how users explore and interact with the world.

To demonstrate this process, the companies developed three example projects. Whiskerhill turns a Marble-generated world into a simple quest-based experience. Whiskerport connects multiple AI-generated scenes into a multi-level environment that users navigate through portals. Clockwork Conspiracy, built by VIVERSE, uses Marble’s generation system to create a more structured, multi-scene game. These projects are not just demos. They serve as proof that AI-generated worlds can evolve beyond static visuals and become interactive environments.

This matters because generative AI is often judged by how quickly it produces content. However, speed alone does not create usable products. Digital experiences still require sequencing, design decisions and user interaction. As a result, the real challenge is not generation, but integration — connecting AI output to tools that make it functional.

Seen in this context, the collaboration is less about a single product and more about workflow. VIVERSE provides a system that allows AI-generated environments to be edited and structured. World Labs provides the engine that creates those environments in the first place. Together, they are testing whether AI can fit directly into a full production pipeline rather than remain a standalone tool.

Ultimately, the collaboration reflects a broader change in creative technology. AI is no longer only producing isolated assets. It is beginning to plug into the larger process of building complete experiences. The key question is no longer how quickly a world can be generated, but how easily that world can be turned into something people can actually use and explore.

Cyber risk is increasingly treated as a financial issue. Boards want to know how much a cyber incident could cost the company, how it could affect earnings, and whether current security spending is justified.

Yet many organizations still measure cyber risk through periodic reviews. These assessments are often conducted once or twice a year, supported by consultants and spreadsheet models. By the time the report reaches senior leadership, the company’s systems may have changed and new threats may have emerged. The way risk is measured does not always match how quickly it evolves.

This gap is where Quantara AI is positioning its new platform. Quantara AI, a Boise-based cybersecurity startup, has introduced what it describes as the industry’s first persistent AI-powered cyber risk solution. The system is designed to run continuously rather than rely on occasional assessments.

The company’s core argument is straightforward: not every security weakness carries the same financial consequence. Instead of ranking issues only by technical severity, the platform analyzes active threats, identifies which company systems are exposed, and estimates how much money a successful attack could cost. It uses statistical models, including Value at Risk (VaR), to calculate potential losses. It also estimates how specific security improvements could reduce that projected loss.

The timing aligns with a broader market shift. International Data Corporation (IDC) projects that by 2028, 40% of enterprises will adopt AI-based cyber risk quantification platforms. These tools convert security data into financial estimates that can guide budgeting and investment decisions. The forecast reflects growing pressure on security leaders to present risk in terms that boards and regulators understand.

Traditional compliance and risk management systems often focus on meeting regulatory standards. Vulnerability management programs typically score weaknesses based on technical characteristics. Consultant-led risk studies provide detailed analysis, but they are usually performed at set intervals. In fast-changing threat environments, that model can leave decision-makers working with outdated information.

Quantara’s platform attempts to replace that periodic process with continuous measurement. It brings together threat data, internal system information and financial modeling in one system. The goal is to show, at any given time, which specific weaknesses could lead to the largest financial losses.

Cyber risk quantification as a concept is not new. What is changing is the expectation that these calculations be updated regularly and tied directly to financial decision-making. As cyber incidents carry clearer monetary consequences, companies are looking for ways to measure exposure with greater precision.

The broader question is whether enterprises will shift fully toward continuous, AI-driven risk analysis or continue relying on periodic external assessments. What is clear is that cybersecurity discussions are moving closer to financial reporting — and tools that estimate potential loss in dollar terms are becoming central to that shift.

‍

Enterprise interest in AI has moved quickly from experimentation to execution. Many organizations have tested generative tools, but turning those tools into systems that can run inside daily operations remains a separate challenge. Cognizant, an IT services firm, is expanding its partnership with Google Cloud to help enterprises move from AI pilots to fully deployed, production-ready systems.

Cognizant and Google Cloud are deepening their collaboration around Google’s Gemini Enterprise and Google Workspace. Cognizant is deploying these tools across its own workforce first, using them to support internal productivity and collaboration. The idea is simple: test and refine the systems internally, then package similar capabilities for clients.

The focus of the partnership is what Cognizant calls “agentic AI.” In practical terms, this refers to AI systems that can plan, act and complete tasks with limited human input. Instead of generating isolated outputs, these systems are designed to fit into business workflows and carry out structured tasks.

To make that workable at scale, Cognizant is building delivery infrastructure around the technology. The company is setting up a dedicated Gemini Enterprise Center of Excellence and formalizing an Agent Development Lifecycle. This framework covers the full process, from early design and blueprinting to validation and production rollout. The aim is to give enterprises a clearer path from the AI concept to a deployed system.

Cognizant also plans to introduce a bundled productivity offering that combines Gemini Enterprise with Google Workspace. The targeted use cases are operational rather than experimental. These include collaborative content creation, supplier communications and other workflow-heavy processes that can be standardized and automated.

Beyond productivity tools, Cognizant is integrating Gemini into its broader service platforms. Through Cognizant Ignition, enabled by Gemini, the company supports early-stage discovery and prototyping while helping clients strengthen their data foundations. Its Agent Foundry platform provides pre-configured and no-code capabilities for specific use cases such as AI-powered contact centers and intelligent order management. These tools are designed to reduce the amount of custom development required for each deployment.

Scaling is another element of the strategy. Cognizant, a multi-year Google Cloud Data Partner of the Year award winner, says it will rely on a global network of Gemini-trained specialists to deliver these systems. The company is also expanding work tied to Google Distributed Cloud and showcasing capabilities through its Google Experience Zones and Gen AI Studios.

For Google Cloud, the partnership reinforces its enterprise AI ecosystem. Cloud providers can offer models and infrastructure, but enterprise adoption often depends on service partners that can integrate tools into existing systems and manage ongoing operations. By aligning closely with Cognizant, Google strengthens its ability to move Gemini from platform capability to production deployment.

The announcement does not introduce a new AI model. Instead, it reflects a shift in emphasis. The core question is no longer whether AI tools exist, but how they are implemented, governed and scaled across large organizations. Cognizant’s expanded role suggests that execution frameworks, internal deployment and structured delivery models are becoming central to how enterprises approach AI.

In that sense, the partnership is less about new technology and more about operational maturity. It highlights how AI is moving from isolated pilots to managed systems embedded in business processes — a transition that will likely define the next phase of enterprise adoption.

Humanoid robotics has advanced quickly in recent years. Machines can now walk, balance, and interact with their surroundings in ways that once seemed out of reach. Yet most deployments remain limited. Many robots perform well in controlled settings but struggle in real-world environments. Integration is often complex, hardware interfaces are closed, software tools are fragmented, and scaling across industries remains difficult.

Against this backdrop, X-Humanoid has introduced its latest general-purpose platform, Embodied Tien Kung 3.0. The company positions it not simply as another humanoid robot, but as a system designed to address the practical barriers that have slowed adoption, with a focus on openness and usability.

At the hardware level, Embodied Tien Kung 3.0 is built for mobility, strength, and stability. It is equipped with high-torque integrated joints that provide strong limb force for high-load applications. The company says it is the first full-size humanoid robot to achieve whole-body, high-dynamic motion control integrated with tactile interaction. In practice, this means the robot is designed to maintain balance and execute dynamic movements even in uneven or cluttered environments. It can clear one-meter obstacles, perform consecutive high-dynamic maneuvers, and carry out actions such as kneeling, bending, and turning with coordinated whole-body control.

Precision is also a focus. Through multi-degree-of-freedom limb coordination and calibrated joint linkage, the system is designed to achieve millimeter-level operational accuracy. This level of control is intended to support industrial-grade tasks that require consistent performance and minimal error across changing conditions.

But hardware is only part of the equation. The company pairs the robot with its proprietary Wise KaiWu general-purpose embodied AI platform. This system supports perception, reasoning, and real-time control through what the company describes as a coordinated “brain–cerebellum” architecture. It establishes a continuous perception–decision–execution loop, allowing the robot to operate with greater autonomy and reduced reliance on remote control.

For higher-level cognition, Wise KaiWu incorporates components such as a world model and vision-language models (VLM) to interpret visual scenes, understand language instructions, and break complex objectives into structured steps. For real-time execution, a vision-language-action (VLA) model and full autonomous navigation system manage obstacle avoidance and precise motion under variable conditions. The platform also supports multi-agent collaboration, enabling cross-platform compatibility, asynchronous task coordination, and centralized scheduling across multiple robots.

A central part of the platform is openness. The company states that the system is designed to address compatibility and adaptation challenges across both development and deployment layers. On the hardware side, Embodied Tien Kung 3.0 includes multiple expansion interfaces that support different end-effectors and tools, allowing faster adaptation to industrial manufacturing, specialized operations, and commercial service scenarios. On the software side, the Wise KaiWu ecosystem provides documentation, toolchains, and a low-code development environment. It supports widely adopted communication standards, including ROS2, MQTT, and TCP/IP, enabling partners to customize applications without rebuilding core systems.

The company also highlights its open-source approach. X-Humanoid has open-sourced key components from the Embodied Tien Kung and Wise KaiWu platforms, including the robot body architecture, motion control framework, world model, embodied VLM and cross-ontology VLA models, training toolchains, the RoboMIND dataset, and the ArtVIP simulation asset library. By opening access to these elements, the company aims to reduce development costs, lower technical barriers, and encourage broader participation from researchers, universities, and enterprises.

Embodied Tien Kung 3.0 enters a market where technical progress is visible but large-scale adoption remains uneven. The gap is not only about movement or strength. It is about integration, interoperability, and the ability to operate reliably and autonomously in everyday industrial and commercial settings. If platforms can reduce fragmentation and simplify deployment, humanoid robots may move beyond demonstrations and into sustained commercial use.

In that sense, the significance of Embodied Tien Kung 3.0 lies less in isolated technical claims and more in how its high-dynamic hardware, embodied AI system, open interfaces, and collaborative architecture are structured to work together. Whether that integrated approach can close the deployment gap will shape how quickly humanoid robotics becomes part of real-world operations.

Algorized has raised US$13 million in a Series A round to advance its AI-powered safety and sensing technology for factories and warehouses. The California- and Switzerland-based robotics startup says the funding will help expand a system designed to transform how robots interact with people. The round was led by Run Ventures, with participation from the Amazon Industrial Innovation Fund and Acrobator Ventures, alongside continued backing from existing investors.

At its core, Algorized is building what it calls an intelligence layer for “physical AI” — industrial robots and autonomous machines that function in real-world settings such as factories and warehouses. While generative AI has transformed software and digital workflows, bringing AI into physical environments presents a different challenge. In these settings, machines must not only complete tasks efficiently but also move safely around human workers.

This is where a clear gap exists. Today, most industrial robots rely on camera-based monitoring systems or predefined safety zones. For instance, when a worker steps into a marked area near a robotic arm, the system is programmed to slow down or stop the machine completely. This approach reduces the risk of accidents. However, it also means production lines can pause frequently, even when there is no immediate danger. In high-speed manufacturing environments, those repeated slowdowns can add up to significant productivity losses.

Algorized’s technology is designed to reduce that trade-off between safety and efficiency. Instead of relying solely on cameras, the company utilizes wireless signals — including Ultra-Wideband (UWB), mmWave, and Wi-Fi — to detect movement and human presence. By analysing small changes in these radio signals, the system can detect motion and breathing patterns in a space. This helps machines determine where people are and how they are moving, even in conditions where cameras may struggle, such as poor lighting, dust or visual obstruction.

Importantly, this data is processed locally at the facility itself — not sent to a remote cloud server for analysis. In practical terms, this means decisions are made on-site, within milliseconds. Reducing this delay, or latency, allows robots to adjust their movements immediately instead of defaulting to a full stop. The aim is to create machines that can respond smoothly and continuously, rather than reacting in a binary stop-or-go manner.

With the new funding, Algorized plans to scale commercial deployments of its platform, known as the Predictive Safety Engine. The company will also invest in refining its intent-recognition models, which are designed to anticipate how humans are likely to move within a workspace. In parallel, it intends to expand its engineering and support teams across Europe and the United States. These efforts build on earlier public demonstrations and ongoing collaborations with manufacturing partners, particularly in the automotive and industrial sectors.

For investors, the appeal goes beyond safety compliance. As factories become more automated, even small improvements in uptime and workflow continuity can translate into meaningful financial gains. Because Algorized’s system works with existing wireless infrastructure, manufacturers may be able to upgrade machine awareness without overhauling their entire hardware setup.

More broadly, the company is addressing a structural limitation in industrial automation. Robotics has advanced rapidly in precision and power, yet human-robot collaboration is still governed by rigid safety systems that prioritise stopping over adapting. By combining wireless sensing with edge-based AI models, Algorized is attempting to give machines a more continuous awareness of their surroundings from the start.

Location trackers have become everyday accessories for keys, bags and luggage. But as personal items grow slimmer and more design-focused — from minimalist wallets to passport sleeves and specialised gear — tracking them has become less straightforward. Most trackers are built as small, rigid discs that assume the presence of space, loops or compartments. That assumption has created a growing mismatch between modern product design and the technology meant to secure it.

Hong Kong–based startup Bitmo Lab is attempting to address that gap with a device called MeetSticker. Instead of the solid plastic casing typical of most trackers, MeetSticker is engineered to be flexible and ultra-thin, measuring just 0.8 millimetres thick. The bendable design allows it to sit within narrow compartments or along curved surfaces without altering the shape of the object. Rather than attaching to an item externally, it is intended to integrate discreetly inside it.

That structural shift is the core of the product’s proposition. By removing the rigid shell that defines conventional tracking hardware, MeetSticker can be placed in items that previously had no practical way to accommodate a tracker. Bitmo Lab states that the device connects through a proprietary network and a companion application compatible with both iOS and Android, positioning it as a cross-platform solution rather than one tied to a single ecosystem.

The implications extend beyond form factor. Objects without obvious attachment points — such as compact travel accessories or specialised tools — could potentially be monitored without visible add-ons. In doing so, the device broadens the scope of tracking technology into categories where aesthetics, aerodynamics or compact design matter as much as functionality.

Before moving toward retail distribution, however, the company is focusing on validation. Bitmo Lab has launched a five-week global alpha testing programme beginning February 9. Sixty participants will receive a prototype unit and early access to the app. According to the company, the programme is designed to assess durability, usability and real-world performance before a wider commercial release. Participants who provide feedback will receive a retail unit upon launch.

Such testing is particularly relevant for flexible electronics. Unlike rigid devices, bendable hardware must withstand repeated flexing, daily handling and environmental exposure. Early user data can help refine manufacturing processes and software optimisation before scaling production.

As with other connected tracking devices, privacy considerations remain part of the equation. Bitmo Lab has stated that data collected during the alpha programme will be used strictly for testing purposes and deleted once the programme concludes.

Whether flexible trackers will redefine the category will depend on how they perform outside controlled testing environments. Still, the introduction of a near-invisible, bendable tracking device reflects a broader shift in consumer technology. As everyday products become thinner and more design-conscious, the tools built to protect them may need to adapt just as seamlessly.

Artificial intelligence is often discussed in terms of large models trained in distant data centres. Less visible, but increasingly consequential, is the layer of computing that enables machines to interpret and respond to the physical world in real-time. As AI systems move from abstract software into vehicles, cameras and factory equipment, the chips that power on-device decision-making are becoming strategic assets in their own right.

It is within this shift that Axera, a Shanghai-based semiconductor company, began trading on the Hong Kong Stock Exchange on February 10 under the ticker symbol 00600.HK. The company priced its shares at HK$28.2, debuting with a market capitalization of approximately HK$16.6 billion. Its listing marks the first time a Chinese company focused primarily on AI perception and edge inference chips has gone public in the city — a milestone that underscores growing investor interest in the hardware layer of artificial intelligence.

The listing comes at a time when demand for flexible, on-device intelligence is expanding. As manufacturers, automakers and infrastructure operators integrate AI into physical systems, the need for specialized processors capable of handling visual and sensor data efficiently has grown. At the same time, China’s domestic semiconductor industry has faced increasing pressure to build local capabilities across the chip value chain. Companies such as Axera sit at the intersection of these dynamics, serving both commercial markets and broader industrial policy priorities.

For Hong Kong, the debut adds to a cohort of technology companies seeking public capital to scale hardware-intensive businesses. Unlike software firms, semiconductor designers operate in a capital-intensive environment shaped by supply chains, fabrication partnerships and rapid product cycles. Their presence on the exchange reflects a maturing investor appetite for AI infrastructure, not just consumer-facing applications.

Axera’s early backer, Qiming Venture Partners, led the company’s pre-A financing round in 2020 and continued to participate in subsequent rounds. Prior to the IPO, it held more than 6 percent of the company, making it the second-largest institutional investor. The public offering provides liquidity for early investors and new funding for a company operating in a highly competitive and technologically demanding sector.

Axera’s market debut does not resolve the competitive challenges of the semiconductor industry, where innovation cycles are short and global competition is intense. But it does signal that investors are placing tangible value on the hardware, enabling AI’s expansion beyond the cloud. In that sense, the listing represents more than a corporate milestone; it reflects a broader transition in how artificial intelligence is built, deployed and financed — moving steadily from software abstraction toward the silicon that makes real-world autonomy possible.

For decades, drug discovery has relied on trial and error, with scientists testing thousands of molecules to find one that works. Galux, a South Korean biotech startup, is changing that by using AI to design proteins from scratch. This method, called “de novo” design, makes it possible to build precise new therapies instead of searching through existing ones.

The company recently announced a US$29 million Series B funding round, bringing its total capital to US$47 million.This significant investment attracted a substantial roster of institutional backers, including the Korea Development Bank (KDB), Yuanta Investment, SL Investment and NCORE Ventures. These firms joined existing investors such as InterVest, DAYLI Partners and PATHWAY Investment, as well as new participants including SneakPeek Investments, Korea Investment & Securities and Mirae Asset Securities.

At the core of the company’s work is a platform called GaluxDesign. Unlike many AI tools that only predict how existing proteins fold, this system uses deep learning and physics to create entirely new therapeutic antibodies. This “from scratch” approach lets the team go after so-called “undruggable” proteins. These are targets that traditional small-molecule drugs can’t reach because they lack clear binding pockets. By designing proteins to fit these complex shapes, Galux aims to unlock treatments that have stayed out of reach for decades. And that’s exactly why investors are paying attention.

The pharmaceutical industry is actively looking for faster and more efficient ways to develop new drugs, and Galux is built for exactly that. The company connects its AI platform directly to its own wet lab, where designs can be tested in real time. Each result feeds straight back into the system, sharpening the next round of models. This continuous loop speeds up discovery and improves precision at every step. It’s also why partners like Celltrion, LG Chem and Boehringer Ingelheim are already working with Galux.

Galux is no longer just trying to make drugs that stick to a target. The company now wants its AI to design medicines that actually work in the body and can be made at scale. In simple terms, a drug has to do more than bind to a disease—it must be stable, safe and strong enough to change how the illness behaves. Galux is moving into tougher targets such as ion channels and GPCRs. These play key roles in heart function and sensory signals. Ultimately, the goal is to show that AI-driven design can turn complex biology into real treatments. And instead of hunting blindly for a solution, the team is building exactly what they need.