Arm Details Its Mobile‑First AI Reconstruction Approach, Distinct from DLSS 5’s Black‑Box Method

Arm, the UK‑based semiconductor and software design powerhouse, recently staged its Arm Everywhere China showcase in Shanghai, unveiling a suite of fresh AI‑computing solutions aimed at the mobile market. Central to the announcement is a comprehensive AI‑native ecosystem that includes the new CSS for Mobile 2 compute platform and the Mali G2‑Ultra NX GPU – a graphics processor built around neural‑accelerated rendering. Arm says this on‑device AI will lift visual performance while keeping power draw and heat generation far lower than traditional approaches, positioning it as a more transparent alternative to Nvidia’s controversial DLSS 5. While Arm did not name specific products that will ship with the Mali G2‑Ultra NX, the predecessor Mali G1‑Ultra already powers devices from Xiaomi, Vivo and OnePlus, suggesting a similar rollout path.

Deyan Lazarov, a member of Arm’s GPU product team within the Edge AI division, explained that development on the G2‑Ultra NX has spanned roughly two and a half years. The chip is intended to give mobile developers access to compute‑heavy features such as real‑time ray tracing, which has historically been limited on phones due to thermal and power constraints.

"We’re seeing a growing appetite for ray tracing in mobile titles," Lazarov noted. "It was slow to gain traction at first, but more developers are now experimenting with it, and the G2‑Ultra NX is designed to support that shift." The new GPU also integrates tightly with Unreal Engine’s advanced features, including MegaLights, and Arm has partnered with Sumo Digital to produce the demo title *Neural Dawn*, which showcases the chip’s capabilities. Lazarov described the target audience as "mobile‑first games that want desktop‑level visual fidelity" as well as cross‑platform experiences that deliver a consistent look and feel whether you’re playing on a console at home or on a train abroad.

Among the titles slated to benefit from the Mali G2‑Ultra NX are Tencent’s *Arena Breakout Infinite*, NetEase’s *Where Winds Meet*, and Infold Games’ *Infinity Nikki*. Lazarov emphasized that phones differ from consoles in two key ways: they have stricter thermal envelopes and they run on batteries, limiting how much heat they can dissipate and how much power they can draw. Arm’s answer is to fuse neural processing with the conventional graphics pipeline.

By offloading portions of the rendering workload to dedicated neuro‑accelerators, the GPU can render fewer native pixels and let AI reconstruct the missing data. This reduces both the raw GPU cycles and the power required, yielding system‑level efficiency gains. "In practice, you get new efficiency that lifts many of the trade‑offs developers normally have to make," Lazarov explained. "They can choose to reinvest the saved budget into higher visual fidelity, smoother performance, longer battery life, or a mix of all three." To make these benefits accessible, Arm is taking an open‑software stance.

Over the past two years the company has built a toolbox of SDKs, plugins and documentation aimed at simplifying AI‑native graphics integration. "We wanted a developer‑friendly AI path that delivers real efficiency gains," Lazarov said. "With those gains, developers can decide where to allocate the extra headroom." Arm’s portfolio includes Neural Super Sampling (NSS), Neural Super Sampling and Denoising (NSSD) and Neural Frame‑Rate Upscaling (NFRU). The technology can upscale lower‑resolution frames, add extra rays for better lighting, and even generate entirely new frames via AI reconstruction.

Lazarov illustrated the process with a two‑frame example: in the first, the GPU renders only a quarter of the image while the neuro‑accelerators fill in the remaining three‑quarters using NSS; in the second, the GPU does no traditional rendering at all, and every pixel is produced by the AI engine. Nvidia’s DLSS 5 also uses AI to enhance images, but Arm deliberately distances its approach from Nvidia’s. "Our networks are not generative; they’re convolutional and trained on real content, not imagined data," Lazarov clarified.

"All of our models are open‑source on GitHub and Hugging Face, so developers can retrain them on their own art styles and retain full IP control." By contrast, DLSS is a closed, proprietary system that operates as a black box; developers cannot see the training data or modify the model. "It’s a take‑it‑or‑leave‑it proposition," Lazarov said, "whereas our solution lets you take the model and tailor it to your game’s unique look." Another major distinction is the mobile‑first design philosophy.

Arm’s networks are built to respect the tight power, bandwidth and memory budgets of phones. "If you tried to run DLSS on a phone, you’d instantly exceed its limits," Lazarov warned.

Arm reports up to four‑times performance and efficiency improvements, along with a 70 % reduction in DRAM traffic—a significant source of power draw on mobile devices. In a head‑to‑head performance story, the previous‑generation GPU could only push *Neural Dawn* to about 40 fps at its limit, dropping to 15 fps under normal conditions. The Mali G2‑Ultra NX, however, can sustain a smooth 60 fps experience with the same title.

From a tooling perspective, Arm currently offers Unreal Engine plugins and plans to expand to Unity and other engines. A recent partnership with Unity China signals that Unity support is on the roadmap, though the immediate focus remains on Unreal. For studios using custom engines, Arm provides an SDK that streamlines integration without requiring a dedicated plugin. Lazarov highlighted that even legacy games can adopt Arm’s AI‑native graphics relatively quickly.

"If you have an existing shipped title and you want to add our solutions, you can have a new version ready in as little as three months," he said. The *Neural Dawn* demo itself was built by a team of fewer than 20 people in under 18 months, demonstrating how Arm’s technology can accelerate development cycles and enable smaller teams to deliver high‑quality, visually impressive experiences. Overall, Arm’s mobile‑first AI reconstruction strategy aims to give developers a transparent, open, and power‑efficient alternative to black‑box solutions, allowing them to push the visual envelope on phones without sacrificing battery life or thermal stability.