𝗣𝗢𝗜𝗡𝗧𝗕𝗟𝗔𝗡𝗞

🦿

NVIDIA just unleashed SANA-WM and it’s an absolute MONSTER for the future of open source AI! A blazing-fast 2.6B-parameter open-source world model that doesn’t just generate video… it creates controllable, physics-rich, high-fidelity worlds on demand. Why this is insanely powerful: • One image + text prompt + 6-DoF camera trajectory → generates 720p videos up to 60 seconds long with buttery-smooth, precisely controlled camera movement. You’re not just watching, you’re piloting the simulation. • Runs locally on a single consumer GPU (RTX 5090 level) thanks to heavy distillation + NVFP4 quantization. Full 60-second clip denoised in ~34 seconds. No massive clusters required. • 36× higher throughput than previous open models while rivaling (or beating) closed industrial giants in visual quality and consistency. • Trained lightning-fast: ~213K public videos in just 15 days on 64 H100s. • Built with next-level tech: Hybrid Linear Attention, dual-branch camera control, two-stage pipeline, and rock-solid metric-scale pose understanding. 
This is a true open world model, the foundation for embodied AI, robotics, autonomous systems, and hyper-realistic simulations that can run anywhere. Project: nvlabs.github.io/Sana/WM/
GitHub: github.com/NVlabs/Sana
Paper: arxiv.org/abs/2605.15178 At our Zero-Human Company, we’re already running SANA-WM live in our core pipelines. It’s supercharging autonomous agent training, generating unlimited synthetic training data, and powering full end-to-end simulation loops, zero humans in the loop. The speed and control let us test thousands of edge-case scenarios overnight, iterate at lightspeed, and push our fully autonomous operations further than ever before. This is the kind of breakthrough that turns science fiction into daily reality. World models just leveled up — hard. The age of personal, local, controllable universes is here.

Robot learned how to moonwalk without being specifically trained.

Transfers 2D image segmentation masks to 3D point clouds github.com/Pointcept/Segm…

Harvesting valuable robot parts.

maybe the real roko's basilisk is the training data we became along the way

Announcing agentive multi drone swarms on Dimensional Agents can coordinate action across multiple robots and write mavlink native physical “skills” Arm(), Takeoff(), Search(), Follow(), GoTo(), Search(), DropPayload() DimOS as the physical harness & hardware guardrail layer

Test it yourself: #slide-id-413493" target="_blank" rel="nofollow noopener">ion.cesium.com/stories/viewer…

DJI's new FC200 four-drone formation: max payload of 600 kg. Unitree's new transformer mecha: 500 kg weight. This is what happens when they work together😏

Meta silently dropped Sapiens2 last week 🔥 a family of high-res models trained on 1B human images > for pose estimation, body-part segmentation, surface normals, pointmaps (sota) > 6 sizes: 0.1B → 5B params (all ViT patch 16) > high-res: 1024×768 and 4K

Rep. Tim Burchett BOMBSHELL: "There are UFO's that have the ability to travel LIGHT YEARS - they will put the war pigs out of business" 👽🛸 “If someone can pierce the veil of government and block access to Congress… who the hell is in control?” He says the Intelligence Community blocked Congress from UFO evidence. Who really holds the power on UAPs? Do you think elected officials are in charge?

SpaceX is considering several locations domestically and internationally to build the world’s most advanced spaceports!

AIメガネのMeta Ray-BanでVPS（カメラで場所を正確に把握する技術）が可能に。 高精度な音声ナビや配車位置特定、複数人での位置共有が可能に。 VPSによる正確な位置の認識により、必要な時と場所で適切なデジタル情報を正確に表示する、新しい空間体験が可能になります。

Next week I'll be growing organs for our humanoid 😎

🔵 3D Gaussian splats are now available in the Cesium and 3D Tiles ecosystems, including CesiumJS, Cesium for Unreal, and Cesium ion. Learn more and get started: cesium.com/blog/2026/04/2…

MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction TL;DR: The first RGB-only multi-agent 3D Gaussian Splatting SLAM for collaborative photorealistic scene reconstruction. Contributions: (1) We propose the first monocular RGB-only multi-agent 3D Gaussian Splatting SLAM system. It integrates Gaussian front-ends, compact submap summaries, inter-agent verification, Sim(3) submap pose graph, and occupancy-aware fusion into a unified framework, achieving accurate tracking and photorealistic reconstruction without depth sensors. (2) We propose a Pose-Graph Bundle Adjustment (PGBA)-consistent Sim(3) loop closure mechanism for multi-agent systems, which jointly resolves intra- and inter-agent scale drift through a submap-level Sim(3) pose graph coupling geometric and photometric residuals. Robustness is ensured by a spatial-extent gate that rejects degenerate loops and an adaptive edge invalidation scheme consistent with evolving PGBA corrections. (3) We propose an occupancy-aware fusion framework for coherent multi-agent Gaussian maps. It combines occupancy-grid deduplication, decoupled coordinator, and joint pose-Gaussian photometric refinement to eliminate duplicated Gaussians, residual misalignment, and photometric seams across agents. (4) We introduce ReplicaMultiagent Plus dataset. While existing multi-agent datasets are typically limited to 2-3 agents with short trajectories, our dataset scales to 4 agents with long-horizon trajectories. In addition, we provide ground-truth geometry and semantic annotations, supporting the evaluation of monocular, RGB-D, and semantic multi-agent SLAM for collaborative dense reconstruction.

@elder_plinius vault -> dropped

one can make an invincible daemon with a single prompt now

I got an email this morning of a new PR against EZ-Tree. Someone added custom rounded normals to the leaves. Looks so damn good I can't get over it! I never knew about this technique. Will get it merged in tonight pending everything looks good.

Introducing Mapbox Atlas v3: self-hosted maps without the infrastructure burden. Atlas v3 is a complete rearchitecture of Atlas — built to dramatically reduce operational overhead while delivering high-quality maps, search, and navigation in secure or disconnected environments. From air-gapped networks to in-vehicle deployments, bring modern mapping to your applications faster and with less complexity. Learn more: mapbox.com/blog/introduci… #BuiltWithMapbox #maps #locationintelligence #selfhosted #webmapping

@asimovinc Next step is in house low cost winding 🛸

Stop training in sim only. Start building hardware. Trust me.