Arm Details Its Mobile‑First AI Reconstruction Approach, Diverging from the "Black Box" Model of DLSS 5

Arm, the British leader in semiconductor and software design, staged its Arm Everywhere China showcase in Shanghai to announce fresh advances in AI‑driven computing. The company’s vision is to build a complete ecosystem for AI‑native workloads, highlighted by the new AI‑centric compute platform CSS for Mobile 2 and the Arm Mali G2‑Ultra NX graphics processor.

This GPU is engineered around neural‑compute blocks, promising higher visual fidelity while keeping thermal output and power draw modest. Arm positions its on‑device AI solution as a more transparent alternative to Nvidia’s controversial DLSS 5, aligning more closely with developers’ original creative intent.

While Arm did not disclose the exact devices that will ship with the Mali G2‑Ultra NX, its predecessor, the Mali G1‑Ultra, already powers smartphones from brands such as Xiaomi, Vivo and OnePlus. Deyan Lazarov, a member of Arm’s GPU product team within the Edge AI division, explained that the Mali G2‑Ultra NX has been in development for roughly two and a half years.

Its purpose is to give mobile developers access to compute‑heavy features—most notably real‑time ray tracing—without the traditional penalties of heat and battery drain. "We’ve seen a steady rise in ray‑tracing adoption on mobile games," Lazarov said. "It was a slow start, but more titles are now actively exploring how to integrate ray‑traced lighting and reflections." According to GamesIndustry.biz, the new GPU enables developers to leverage Unreal Engine capabilities such as MegaLights.

Arm partnered with Sumo Digital to produce the demo title *Neural Dawn*, which serves as a practical showcase of the Mali G2‑Ultra NX’s capabilities. Lazarov emphasized that the chip targets games that are "mobile‑first but aspire to look like desktop‑class experiences," as well as cross‑platform titles that aim for a seamless visual experience whether played on a console at home or on a train abroad.

A handful of upcoming games are slated to use the new hardware, including Tencent’s *Arena Breakout Infinite*, NetEase’s *Where Winds Meet*, and Infold Games’ *Infinity Nikki*. Lazarov noted the unique constraints of smartphones: unlike consoles or PCs, phones cannot dissipate large amounts of heat and must constantly run on battery power. Arm’s answer is to fuse neural processing directly into the conventional rendering pipeline.

By offloading portions of the workload to dedicated neuro‑accelerators, the GPU’s power consumption drops, which in turn improves overall system efficiency. "This new efficiency lifts many of the trade‑offs developers usually face," Lazarov explained. "They can allocate saved resources to higher visual fidelity, better performance, longer battery life, or any combination they prefer." To foster adoption, Arm is taking an open‑software stance, releasing a suite of tools and making its AI models publicly available.

"We’ve spent the last two years collaborating with the ecosystem to create a developer‑friendly AI workflow," Lazarov said. "Our goal is to give developers the ability to reap massive efficiency gains and then decide how to reinvest those gains—whether in graphics quality, frame‑rate, or power savings." Arm’s portfolio includes Neural Super Sampling (NSS), Neural Super Sampling and Denoising (NSSD), and Neural Frame‑Rate Upscaling (NFRU). These technologies can upscale lower‑resolution images, add extra rays for richer lighting, and generate additional frames through AI‑based reconstruction. Lazarov illustrated the process with two example frames: in the first, the GPU renders only 25 % of the image while the neuro‑accelerators reconstruct the remaining three‑quarters via NSS; in the second, the entire frame is produced by the AI engine with no traditional rasterization at all.

Nvidia’s DLSS 5 also employs AI to enhance image detail, but it has drawn criticism for its “black‑box” nature and for sometimes diverging from the creator’s artistic intent. Arm deliberately distances itself from that model. "Our networks are not generative; they are convolutional and do not invent content," Lazarov clarified. "They have been trained on real‑world data and are released openly on GitHub and Hugging Face.

Developers can even fine‑tune the models with their own art‑style datasets, preserving IP and ensuring the upscaled output matches their vision." By contrast, DLSS is proprietary, closed, and cannot be retrained by developers. "It’s a take‑it‑or‑leave‑it solution," Lazarov said, emphasizing that Arm’s approach lets developers customize the AI to their specific aesthetic needs. Another key distinction is mobile‑first design.

Arm’s networks are built with strict power, bandwidth, and memory budgets in mind. "If you tried to run DLSS on a phone, you’d instantly exceed its limits," Lazarov warned.

The Mali G2‑Ultra NX delivers up to four times the performance and efficiency of its predecessor, while cutting DRAM traffic by roughly 70 %, a major source of power consumption on handheld devices. In practical terms, the older GPU could only push *Neural Dawn* to about 40 fps at its limit and dropped to 15 fps under normal conditions. The new Mali G2‑Ultra NX comfortably reaches 60 fps, delivering a smoother experience without sacrificing battery life. Arm is already providing Unreal Engine plug‑ins and plans to extend support to Unity and other engines.

A recent partnership with Unity China signals that broader engine integration is on the roadmap. For studios using custom engines, Arm offers an SDK that streamlines integration without requiring bespoke plug‑ins. Lazarov highlighted that existing titles can adopt Arm’s AI‑native graphics relatively quickly.

"Porting our solution into an already shipped game can take as little as three months," he noted. The *Neural Dawn* demo itself was built by a team of fewer than 20 developers in under 18 months, illustrating how Arm’s tools can accelerate development cycles while enhancing visual quality. Overall, Arm’s strategy combines open‑source AI models, mobile‑centric efficiency, and flexible tooling to give developers a transparent, customizable path to high‑quality graphics on smartphones, positioning the Mali G2‑Ultra NX as a compelling alternative to the closed, console‑focused DLSS paradigm.