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

Arm, the British semiconductor and software design powerhouse, staged its Arm Everywhere China showcase in Shanghai to announce a suite of fresh AI‑computing innovations. Central to the reveal is a comprehensive AI‑native ecosystem that includes the new CSS for Mobile 2 compute platform and the Arm Mali G2‑Ultra NX graphics processor. This GPU is built around neural‑computing principles, promising higher graphical performance while dramatically cutting heat output and power draw.

Arm positions its on‑device AI solution as a more transparent alternative to Nvidia’s contentious DLSS 5, aligning more closely with developers’ original creative intentions. 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 phones from 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. The chip is designed to let mobile developers harness compute‑heavy techniques such as ray tracing, which has recently begun to gain traction in smartphone titles.

"We’re seeing a growing appetite for ray tracing on mobile," Lazarov said. "It’s been a slow burn, but more developers are now eager to enable it in their games." The new GPU integrates with Unreal Engine features like MegaLights, and Arm collaborated with Sumo Digital to produce the demo title Neural Dawn, which showcases the processor’s capabilities. Lazarov emphasized that the chip targets games that are "mobile‑first but want desktop‑level visual fidelity." He also highlighted cross‑platform experiences, noting that players should enjoy a consistent quality whether they are gaming on a console at home or on a train in London. Titles slated to benefit from the Mali G2‑Ultra NX include Tencent’s Arena Breakout Infinite, NetEase’s Where Winds Meet, and Infold Games’ Infinity Nikki.

Mobile devices face unique thermal and power constraints compared with consoles or PCs. "A phone can’t dissipate heat the way a console can, and it runs constantly on a battery," Lazarov explained. Arm’s answer is to blend neural processing with the traditional rendering pipeline.

By offloading portions of the workload to dedicated neuro‑accelerators, the GPU’s power consumption drops, leading to system‑wide efficiency gains. This reduces the need for developers to make the usual trade‑offs between visual quality, performance, and battery life. To make AI‑native graphics attractive to developers, Arm is taking an open‑software stance and supplying a robust toolset.

"We’ve spent the last two years working closely with the ecosystem to create a developer‑friendly AI workflow," Lazarov said. "The idea is to give developers the ability to reallocate the efficiency gains toward higher fidelity, better performance, longer battery life, or any combination they prefer." Arm’s portfolio includes Neural Super Sampling (NSS), Neural Super Sampling and Denoising (NSSD), and Neural Frame Rate Upscaling (NFRU).

These technologies can upscale images, add extra rays, and generate new frames via AI reconstruction. Lazarov illustrated the process with two example frames: in the first, the GPU renders only a quarter of the image while the neuro‑accelerators reconstruct the remaining three‑quarters using NSS. In the second frame, the entire image is produced by the neuro‑accelerators, with the GPU performing no traditional rendering at all.

Nvidia’s DLSS 5 also uses AI to enhance images, but it has drawn criticism for potentially diverging from developers’ artistic intent. Arm draws a clear line between its approach and Nvidia’s.

"Our networks are not generative; they’re convolutional, meaning they don’t invent new content, they simply know how existing content should look," Lazarov explained. "We train them on real data and make the models publicly available on GitHub and Hugging Face." This openness lets developers capture datasets from their own games, retrain the models, and ensure the upscaled or interpolated frames match their unique art style. "Because you do the retraining, there’s no risk of losing IP control," he added.

By contrast, DLSS is a closed, proprietary system that developers cannot modify or inspect, offering a "take it or leave it" proposition. Another distinction is mobile suitability.

Arm’s networks are engineered with phone‑level constraints—power, bandwidth, and thermal budgets—in mind. "DLSS would simply blow past a phone’s limits," Lazarov said. "Our solution is designed to fit within those tight constraints." Power efficiency is a cornerstone of the Mali G2‑Ultra NX.

Arm reports up to four‑times performance and efficiency improvements, plus a 70 % reduction in DRAM traffic, one of the biggest power drains on mobile devices. Less memory access translates directly into lower energy consumption.

In practical terms, the performance jump is stark. Running Neural Dawn on the previous generation GPU capped at about 40 fps under ideal conditions and fell to roughly 15 fps in typical use.

The new Mali G2‑Ultra NX can comfortably sustain 60 fps, delivering a smoother experience. Arm is also delivering development support. Plug‑ins for Unreal Engine are already available, and a Unity plug‑in is on the roadmap, following a recent partnership with Unity China. For studios using custom engines, Arm provides an SDK that offers a streamlined integration path.

Lazarov noted that existing games can be upgraded with Arm’s AI‑native graphics relatively quickly. "Integrating our solution into a shipped title can take as little as three months to release a new version with these enhancements," he said.

The Neural Dawn demo itself was built by a team of fewer than 20 people in under 18 months, illustrating how Arm’s technology can accelerate development cycles and enable smaller teams to produce visually impressive, efficient games. In summary, Arm’s mobile‑first AI reconstruction strategy offers an open, developer‑centric alternative to Nvidia’s DLSS 5. By combining neural upscaling, denoising, and frame‑rate generation with a power‑aware architecture, the Mali G2‑Ultra NX aims to bring desktop‑grade graphics to smartphones without sacrificing battery life or thermal stability, while giving developers full control over the visual outcome.