XGEN Labs

From Pixels to Worlds,
from Intelligence to Life.

[XGEN Labs @XGEN_labs]

@iamsania_AI We maintain a single authoritative world state, which is projected to each agent as a stream of multimodal conditions, including camera geometry, reference imagery, and textual descriptions. Each agent only receives its local view, while the underlying world state remains shared.

[XGEN Labs @XGEN_labs]

More on the technical thinking behind our generative world simulation approach, including JING and DAO:

📖 Read the full blog:
https://t.co/HX946xG2JW

[XGEN Labs @XGEN_labs]

🔥 Today, we are truly excited to announce our technical prototype, the Generative World Simulation system, which integrates JING（镜）, an interactive experience model, with DAO（道）, a computable shared-world engine.

The coupled model and engine connect first-person experience with a shared world that continues to evolve beyond any individual observer.

Conditioned on actions and observation history, JING enables agent navigate, manipulate, and communicate from a first-person perspective in the world. Watch our demo video to see it in action!

On the official WBench leaderboard as of September 17, 2026, XGEN-JING ranked #1 on the Full split, and #2 on the Navi split. 🎉

DAO maintains shared world state and rules, computes the consequences of actions, and provides JING with only what the current observer can perceive. It also supports autonomous agent decision-making, enabling agents to act independently within an evolving shared world.

Together, DAO and JING move beyond generating the next frame toward simulating the world behind it. This marks a small step towards OASIS: not just a world that responds to you, but a world—and a society—that evolves with and without you. 💪

Explore XGEN Labs～:

🔗 Website: https://t.co/tqTvPIk19B

🤗 HF: https://t.co/wxLRmJNYgO

🦊 GitHub: https://t.co/2DMvURLUsK

[XGEN Labs @XGEN_labs]

AI can generate images.
AI can generate videos.

But the world is more than content.
It is dynamic. Interactive. Persistent.

We’re building AI that can simulate worlds.

From generating content to simulating worlds.

This is XGEN.

Explore more → https://t.co/NZPnxgM6Jv

[XGEN Labs @XGEN_labs]

https://t.co/pbKiZuRsPd

[XGEN Labs @XGEN_labs]

https://t.co/pbKiZuRsPd

[Runway @runwayml]

We believe instant generation is where video models are headed. Last week, we released Solaris and GWM Worlds 2, and detailed our approach to agent training in digital and physical worlds. Today, we’re sharing a broader look at our research efforts in real-time video generation.

Read more at the link below.
https://t.co/qpbJ33gYy2

[XGEN Labs @XGEN_labs]

@c_valenzuelab Amazing progress.

[XGEN Labs @XGEN_labs]

@munzxsdv Exactly. The shift from generating frames to simulating worlds is where things get really interesting.

[XGEN Labs @XGEN_labs]

@higgsfield wow，this is a fascinating step from 3D visualization toward truly interactive environments.

[XGEN Labs @XGEN_labs]

@taiuti @reactorworld 👍👍

[XGEN Labs @XGEN_labs]

@xing_rui12683 @theworldlabs @Hailuo_AI @xieenze_jr Reconstructing a scene is one thing. Understanding how the world behaves and enabling interaction is another. That distinction feels central to Spatial Intelligence.

[XGEN Labs @XGEN_labs]

@xieenze_jr @MiniMax_AI Amazing progress!

[XGEN Labs @XGEN_labs]

@duncantrussell This feels like a step from generating content to generating the world behind the content.

[XGEN Labs @XGEN_labs]

@BenMildenhall The move from image generation to controllable 3D worlds is especially exciting. Curious how far this kind of world knowledge can generalize across unseen environments and viewpoints.

[hedoήist @hedo_ist]

Which is the best colossal scene? ❤️‍🔥

1 - Stay Focused (Poetic sci-fi)
2 - Epic (intimidating architecture)
3 - Chromatic cyberpunk
4 - Mythology: Mermaids at play

Photos in the comments 👇

Created with @grok & Midjourney 8.2

[Hoogarden @0xHoogarden]

PHYSICAL AI IS LEARNING TO TOUCH, MOVE, THINK AND SOMETIMES MAKE VERY HUMAN MISTAKES

Physical AI is giving robots something previous generations of AI never truly had: the ability to interact with reality. Instead of simply generating an answer, a robot can look around, understand what it sees, decide what to do, reach for an object, move through a space, and actually change its environment.

And that changes everything.

A digital AI can make a wrong prediction and generate another response. A physical AI has to deal with gravity, friction, distance, weight, obstacles, fragile objects, moving people and the consequences of every decision it makes.

That’s why watching these robots learn is so fascinating. Every successful movement is progress. Every strange mistake reveals another limitation that engineers have to solve.

We’re moving from AI that knows things to AI that can do things.

And once robots can reliably understand the physical world, they won’t just be machines in factories. They could become workers, assistants, operators, and autonomous systems capable of performing real jobs alongside humans.

PHYSICAL AI IS THE MOMENT INTELLIGENCE LEAVES THE SCREEN AND ENTERS THE REAL WORLD.

The question is no longer “Can AI think?”

It’s “What happens when AI can think and physically act on its decisions?”

[闇堕ちネネちゃん @Tiktoktrend2026]

技術が発達するのはいいことばかりではなさそう

[XGEN Labs @XGEN_labs]

@_mario_boss 🤣