Technology

Narrative Unveils LLM Fine-Tuning Platform and Rosetta Stone 2.0, Pioneering a New Era of Data Normalization and Custom Model Training

Published

1 year ago

January 7, 2025

NEW YORK, Jan. 7, 2025 /PRNewswire/ — Narrative, the industry’s leading data collaboration and commerce platform, today announced a groundbreaking suite of enhancements aimed at democratizing AI development and data utilization. Chief among these is the introduction of a new Large Language Model (LLM) fine-tuning capability, enabling companies of all sizes to customize their own AI models directly on the Narrative platform with unprecedented ease. Additionally, Narrative is thrilled to introduce Rosetta Stone™ 2.0, the next generation of the company’s acclaimed data normalization solution, engineered using the very fine-tuning tools now available to customers.

Narrative Unveils LLM Fine-Tuning Platform & Rosetta Stone 2.0, Revolutionizing Data Normalization & AI Customization

A Collaborative and Accessible Approach to LLM Fine-Tuning
At the core of Narrative’s approach is a “collaboration-first” philosophy. Users can now access a broad range of datasets—from proprietary and partner sources to publicly available and marketplace content—to train and refine their LLMs. This approach fosters an ecosystem where content creators and publishers can monetize their work directly, while businesses benefit from a richer, more diverse data pool to power increasingly sophisticated AI models. By removing technical barriers and simplifying the model-building process, Narrative empowers everyone from non-technical operators to seasoned data scientists to craft bespoke language models with a simple point-and-click interface.

Rosetta Stone 2.0: Next-Generation Data Normalization
A centerpiece of today’s announcement is Rosetta Stone 2.0, an evolution of Narrative’s pioneering data normalization capability. Leveraging Narrative’s new LLM fine-tuning platform, the updated Rosetta Stone model delivers remarkable performance gains and expanded functionality. It not only standardizes data automatically across disparate sources, ensuring seamless compatibility and readiness for training, but it also can serve as a foundational base model for customers looking to extend its core normalization capabilities into their specific domain. From ensuring coherent data formats to tackling complex, domain-specific semantic challenges, Rosetta Stone 2.0 is a flexible, next-level tool designed to accelerate data-driven innovation.

Key Features and Benefits:

Easy, No-Code Model Fine-Tuning:
Users can skip the complex coding, configuration files, and intricate infrastructure setups. Narrative’s platform translates raw datasets into meaningful training material through an intuitive, point-and-click interface.

Rich Data Ecosystem & Monetization Opportunities:
Through Narrative’s marketplace, publishers, content creators, and data owners can directly profit by offering their datasets for model training. Simultaneously, developers can tap into a vast reservoir of high-quality information to train models that align perfectly with their use cases.

Rosetta Stone 2.0 Engineered with Fine-Tuning:
Built using the same LLM customization features now offered to users, Rosetta Stone 2.0 exemplifies the power and potential of the Narrative platform. Its advanced normalization techniques handle complex and heterogeneous data sets, and it can be adapted into a specialized normalization model for industry- or business-specific contexts.

Bring fine tuning to your data
Narrative fine tuning is available anywhere Narrative is available, including in Narrative’s cloud and in your organization’s Snowflake, Databricks, AWS, Azure, or GCP account.

Customizing Rosetta Stone for Your Data

Narrative now gives you the option to tailor Rosetta Stone’s powerful data normalization capabilities so it fits your organization’s unique data and terminology—no major system overhauls required. This means you get more accurate and consistent results by aligning Rosetta Stone with your own industry language and internal structures.

When you’re ready to deploy Rosetta Stone, you can choose from different model sizes to strike the right balance of speed, detail, and cost. Simply pick the option that best fits your team’s priorities and infrastructure.

“The launch of our LLM fine-tuning platform and Rosetta Stone 2.0 marks a pivotal milestone in our journey to democratize AI development. With these offerings, anyone can create, refine, and extend powerful language models, and content creators can finally realize tangible value for their contributions. This is what the future of data and AI collaboration looks like—accessible, flexible, and mutually beneficial for all stakeholders.” –Nick Jordan, Founder, Narrative

For more information on Narrative’s LLM fine-tuning platform and Rosetta Stone 2.0, or to schedule a live demo, visit narrative.io.

View original content to download multimedia:https://www.prnewswire.com/news-releases/narrative-unveils-llm-fine-tuning-platform-and-rosetta-stone-2-0–pioneering-a-new-era-of-data-normalization-and-custom-model-training-302344342.html

SOURCE Narrative I/O, Inc.

Technology

Chef Robotics Physical AI Models Can Now Automate Baked Goods Packing

Published

3 hours ago

April 29, 2026

SAN FRANCISCO, April 29, 2026 /PRNewswire/ — Chef Robotics, a leader in physical AI for the food industry, today announced that Chef robots can now automate tray assembly for baked goods packing. The application places baked products, such as burger buns, chocolate chip cookies, biscotti, butter cookies, biscuits, fortune cookies, granola bars, rusks, and shortbreads into trays and packaging containers before sealing.

Watch Chef robots in action.

Baked goods packing has historically been difficult to automate for high-mix production. Each item behaves differently on the production line—a granola bar compresses under the wrong grip, while a biscotti or rusk can crack if placed at the wrong angle. Surface textures range from glazed and smooth to crumbly and irregular, and strict presentation requirements leave little room for error. This variability has made it challenging for automation systems to reliably handle baked goods at production speeds, leaving food manufacturers dependent on manual labor and traditional bakery equipment.

To address this, Chef built its baked goods packing application on its existing piece-picking capability, which uses Chef’s AI-powered computer vision and physical AI models trained across diverse real-world production environments. This allows Chef robots to assess each item’s position, shape, and orientation in real time and determine how to pick the items from the pan and place them quickly and precisely without damaging them.

The baked goods packing application supports four distinct placement capabilities.

First, Chef’s vision system detects the angle at which each item sits in the pan and reorients it after picking, placing it on the tray at the exact angle required, regardless of its original position, enabling retail-ready presentation for SKUs that require precise angular placement.

Second, Chef robots can place multiple baked goods into the same packaging container in a single automated pass, completing full tray assembly without manual intervention.

Third, for packaging containers with multiple small compartments, Chef robots can precisely place items into each designated section, including multiple items in the same compartment, using Chef’s AI vision model to detect compartment positions and orientations in real time.

Fourth, Chef’s vision system identifies the exact center of each tray and places every item at a predefined offset from that center, ensuring a uniform, consistent arrangement across every pack regardless of how trays arrive on the conveyor.

For food manufacturers evaluating bakery systems and baked goods packaging automation, the application offers higher throughput, reduced labor dependency, and consistent presentation across shifts. The capability runs on Chef’s existing robotic hardware and software, allowing manufacturers to deploy it without requiring any changes to their production lines.

Chef’s baked goods packing application is available in the U.S., Canada, Germany, and the UK and is included as part of Chef’s robotics-as-a-service (RaaS) pricing model.

About Chef Robotics
Chef is the first company to have commercialized a scalable AI-driven food robotics solution. With over 104 million servings made in production, Chef leverages ChefOS, an AI platform for food manipulation, to offer a Robotics-as-a-Service solution that helps industry-leading food companies increase production volume and meet demand. Headquartered in San Francisco, CA, Chef aims to empower humans to do what humans do best by accelerating the advent of intelligent machines. Visit https://chefrobotics.ai to learn more.

View original content:https://www.prnewswire.com/news-releases/chef-robotics-physical-ai-models-can-now-automate-baked-goods-packing-302756923.html

SOURCE Chef Robotics

Technology

Chef Robotics Physical AI Models Can Now Automate Baked Goods Packing

Published

3 hours ago

April 29, 2026

Watch Chef robots in action.

The baked goods packing application supports four distinct placement capabilities.

Second, Chef robots can place multiple baked goods into the same packaging container in a single automated pass, completing full tray assembly without manual intervention.

Chef’s baked goods packing application is available in the U.S., Canada, Germany, and the UK and is included as part of Chef’s robotics-as-a-service (RaaS) pricing model.

View original content:https://www.prnewswire.com/news-releases/chef-robotics-physical-ai-models-can-now-automate-baked-goods-packing-302756923.html

SOURCE Chef Robotics

Technology

Air Products to Expand Industrial Gas Supply for Samsung Electronics’ Next-Generation Semiconductor Fab in South Korea

Published

3 hours ago

April 29, 2026

New investment underscores the company’s long-term commitment to Korea and its leading role in the global semiconductor industry

LEHIGH VALLEY, Pa., April 29, 2026 /PRNewswire/ — Air Products (NYSE:APD), a world-leading industrial gases company and serving Samsung globally, today announced it has been selected by Samsung to supply industrial gases for its new advanced semiconductor fab in Pyeongtaek, Gyeonggi Province, South Korea.

Under the agreement, Air Products will build, own and operate multiple state-of-the-art production facilities and a bulk specialty gas supply system to supply nitrogen, oxygen, argon, and hydrogen for Samsung’s new semiconductor fab. The new facilities are expected to come onstream in multiple phases from 2028 through 2030.

Air Products has a long track record of executing multiple phase expansions in Pyeongtaek to support Samsung’s growing manufacturing needs. This latest project represents Air Products’ largest investment to date in the semiconductor industry and will establish Pyeongtaek as the company’s single largest operations site globally supporting the electronics industry.

“Air Products is honored to be selected once again by Samsung and to have their continued confidence as a trusted partner supporting their strategic growth plans,” said SR Kim, President, Air Products Korea. “This significant investment reinforces Air Products’ role as a leading global supplier to the semiconductor industry and underscores our long-standing commitment to supporting our strategic customers with safety, reliability, efficiency and excellent service.”

Air Products has served the global electronics industry for more than 40 years, supplying industrial gases safely and reliably to many of the world’s leading technology companies. The company has operated in Korea for more than 50 years and has established a strong position in electronics and manufacturing sectors.

About Air Products

Air Products (NYSE: APD) is a world-leading industrial gases company in operation for over 85 years focused on serving energy, environmental, and emerging markets and generating a cleaner future. The Company supplies essential industrial gases, related equipment and applications expertise to customers in dozens of industries, including refining, chemicals, metals, electronics, manufacturing, medical and food. As the leading global supplier of hydrogen, Air Products also develops, engineers, builds, owns and operates some of the world’s largest clean hydrogen projects, supporting the transition to low- and zero-carbon energy in the industrial and heavy-duty transportation sectors. Through its sale of equipment businesses, the Company also provides turbomachinery, membrane systems and cryogenic containers globally.

Air Products had fiscal 2025 sales of $12 billion from operations in approximately 50 countries. For more information, visit airproducts.com or follow us on LinkedIn, X, Facebook or Instagram.

This release contains “forward-looking statements” within the safe harbor provisions of the Private Securities Litigation Reform Act of 1995. These forward-looking statements are based on management’s expectations and assumptions as of the date of this release and are not guarantees of future performance. While forward-looking statements are made in good faith and based on assumptions, expectations and projections that management believes are reasonable based on currently available information, actual performance and financial results may differ materially from projections and estimates expressed in the forward-looking statements because of many factors, including the risk factors described in our Annual Report on Form 10-K for the fiscal year ended September 30, 2025 and other factors disclosed in our filings with the Securities and Exchange Commission. Except as required by law, we disclaim any obligation or undertaking to update or revise any forward-looking statements contained herein to reflect any change in the assumptions, beliefs or expectations or any change in events, conditions or circumstances upon which any such forward-looking statements are based.

View original content to download multimedia:https://www.prnewswire.com/news-releases/air-products-to-expand-industrial-gas-supply-for-samsung-electronics-next-generation-semiconductor-fab-in-south-korea-302757497.html

SOURCE Air Products