इस साइट की सामग्री का अनुवाद कृत्रिम बुद्धिमत्ता (AI) या मशीन अनुवाद तकनीक का उपयोग करके किया गया है, और इसमें त्रुटियाँ हो सकती हैं.

Skip to content

Pioneering AI Founders Join to Accelerate Roblox Reality Vision

Founders From Morpheus AI, Dynamics Lab, Lucid AI Make Playable Photorealistic Roblox World Models Possible

Pioneering AI Founders Join to Accelerate Roblox Reality Vision

The path to true interactive AI will have to address three major hurdles: latency, consistency, and quality. With the acquisition of Morpheus AI's team and technology, alongside the expertise of Dynamics Lab and Lucid AI founders, Roblox is now one step closer to realizing our interactive AI vision. For too long, video models have been trapped in slow, bidirectional offline generation. Through years of post-training experimentation, researcher Xun Huang achieved a breakthrough and invented Self Forcing, a revolutionary recipe to convert sluggish offline video models into fast, autoregressive, interactive generation engines. Armed with this breakthrough, Huang founded Morpheus AI in relentless pursuit of real-time responsiveness. This key technology serves as the foundation built by a remarkably strong team of researchers at Morpheus AI.

Morpheus AI’s original objective—training an egocentric video world model purely in pixel latent space to simulate real-world dynamics and physics—finds its ultimate realization in Roblox Reality. At Roblox, we’ve realized that standalone world models, while powerful, fundamentally lack the long-term memory, consistent logic, and structured user input required for a massive multiplayer platform. This is where a convergence with Roblox’s Engine becomes a clear opportunity. Our intent is that Morpheus AI’s models will accelerate the evolution towards Roblox Reality’s Roblox Video Model (Super Upsampler) technology, layering on the visual components, including higher-fidelity textures, realistic lighting, and fluid physics, while the Roblox Engine manages the structured, symbolic logic and multiplayer state synchronization.

But Morpheus and Huang’s groundbreaking work is just one element of the wider AI innovation at Roblox. 

In late 2025, Dynamics Lab founder Joe Chen joined forces with Roblox. At Dynamics Lab, Chen and his team focused on building a powerful, flexible, and responsive real-time, general-domain generative world engine. It allowed users to upload any image—photos, concept art, classic paintings, kids' drawings—and step into it as a live, interactive world. Users could prompt their worlds with text to create any surreal scene or wild event, then share a link for friends to jump in and play instantly. 

The founder of Lucid AI, Alberto Hojel also joined Roblox in late 2025. Hojel founded Lucid AI on the principle that AI-generated worlds needed to be reliable and consistent, where stunning visuals were balanced with deterministic game logic. Hojel recognized that while video world models could generate impressive, physics-rich realities, they fundamentally lacked the long-term state and predictable progression required for a true game. Based on this founding principle Hojel has invented the Roblox game cartridge harness: augmenting video world models with the reliable, deterministic logic of a dedicated game engine like Roblox’s. This key convergence is what transforms a mere explorable world into a high-fidelity, interactive, multiplayer gaming platform.

The ambition of the Roblox Reality architecture—achieving 4K resolution at 60 Hz—is an unprecedented technical innovation for video world models. This is why deep expertise in optimization and KV compression is so critical. We’re moving the Roblox Video Model (Super Upsampler) to adjacent edge data centers powered by H200/B200-class GPUs. For example, the work by Morpheus AI pioneered the long context abilities of world models. This will be vital for maintaining visual consistency across the immersive experiences Roblox creators will build.

The integration of game engine and video models is the missing piece to unlocking consistent photorealistic multiuser worlds. This hybrid architecture combines the structured simulation power of the Roblox Engine with the generative vision of Morpheus AI world models. Building a team of innovative founders creates a talent-dense environment that accelerates innovation and streamlines development of high-fidelity, interactive world creation. 

We’re incredibly excited for these leading AI innovators to join forces with Roblox. We’re ready to put technologies like Self Forcing and pixel-latent world models to work, building the foundational layers of photorealistic multiplayer games. Stay tuned for the transformative moments ahead.