Voxel Voyager

Building world models and simulations for AI agents and robotics.

[Voxel Voyager @voxagent_dev]

@graildoteth @hytopia Do you think you could step in to help save HYTOPIA, like Simon (@Simon_Hypixel) did with Hytale?
The engine still has strong potential, and I think the community and stakeholders would be ready to contribute.

[汗青 HQ @hq4ai]

尤栗Yuri为Seedance2.0创作的主题单曲MV来了。
我们用各种方法把SD2.0的效果压到极限。口型、弹唱、动作、仙侠、舞团…这确实是AI影像和MV的新时代。
打算开个帖子详细聊聊SD2.0使用中的一些细节体会，另外今天火山也开放了SD2.0的接口，新时代开启。

[Jim Fan @DrJimFan]

The power of the Claw, in the palm of a robot hand. Agentic robotics is here! Today, we open-source CaP-X: vibe agents, alive in the physical world. They incarnate as robot arms and humanoids with a rich set of perception APIs, actuation APIs, and auto synthesize skill libraries as they go. CaP-X is a strict superset of our old stack, because policies like VLAs are “just” API calls as well. It solves many tasks zero-shot that a learned policy would struggle with.

And we are doing much more than vibing. CaP-X is our most systematic, scientific study on agentic robotics so far:

- We build a comprehensive agentic toolkit: perception (SAM3 segmentation, Molmo pointing, depth, point cloud), control (IK solvers, grasp planner, navigation), and visualization (EEF, mask overlays) that work across different robots.
- CaP-Gym: LLM’s first Physical Exam! 187 manipulation tasks across RoboSuite, LIBERO-PRO, and BEHAVIOR. Tabletop, bimanual, mobile manipulation. Sim and real. Can’t wait to see the gradients flow from CaP-Gym to the next wave of frontier LLM releases.
- CaP-Bench: we benchmark 12 frontier LLMs/VLMs (Gemini, GPT, Opus, Qwen, DeepSeek, Kimi, and more) across 8 evaluation tiers. We systematically vary API abstraction level, agentic harness, and visual grounding methods. Lots of insights in our paper.
- CaP-Agent0: a training-free agentic harness that matches or exceeds human expert code on 4 out of 7 tasks without task-specific tuning.
- CaP-RL: if you get a gym, you get RL ;). A 7B OSS model jumps from 20% to 72% success after only 50 training iterations. The synthesized programs transfer to real robots with minimal sim-to-real gap.

3 years ago, our team created Voyager, one of the earliest agentic AI that plays and learns in Minecraft continuously. Its key ideas — skill libraries, self-reflection loops, and in-context planning — have since influenced many modern agentic designs.

Today, the agent graduates from Minecraft and gets a real job. It’s April Fool’s, but this Claw is getting its hands dirty for real!

Link in thread:

[Hugo @robonaissance]

The Multimodal Future: Why Visual Representation Still Matters, by Saining Xie (@sainingxie)

https://t.co/m0zisjJqrM

[Hugo @robonaissance]

I’ve started a new four-part deep dive series exploring a fascinating seven-hour interview with Saining Xie, hosted by Xiaojun Zhang.

https://t.co/NR2cwWWyWe

Saining Xie, cofounder and chief science officer of AMI Labs, believes the AI industry’s most successful technology is also its most seductive trap. His company has just raised $1.03 billion to prove it.

[Voxel Voyager @voxagent_dev]

A billion dollars on a single question: does the order in which a machine learns determine how well it understands?

[Hugo @robonaissance]

https://t.co/ajNjL3Lac6

[Voxel Voyager @voxagent_dev]

@steipete Swarm Intelligence 2.0🦞
https://t.co/M6s9OhilA1