Kickoff of day 1 at @CoreWeave Hacks. 200+ builders, one mission: build an agent loop that catches its own mistakes. @agihouse_org, @typesafeai and @marimo_io are here with $1k+ in credits and tons of compute. 24 hours to submit. One team is going home with a robot dog!

Marigold V2 turns an image-editing DiT into a single-step model for sharp, detailed dense prediction.📜 Apache 2.0. 🤖 📄 🏆 Best zero-shot results across all evaluated depth datasets among models trained on comparable data. AbsRel improves by 16%–26% over the previous best on KITTI and ETH3D. 🔍 Fur, foliage, fine wires, and object boundaries stay crisp. The two-stage iREPA and SinkLoss recipe tackles the smoothing and flying-pixel artifacts common in diffusion-based depth models. 🧩 The same framework reaches SOTA results in depth completion, see-through depth, surface normals, and intrinsic image decomposition. Depth completion records the lowest RMSE across all four reported benchmarks. ⚡ A pretrained Qwen-Image-Edit DiT becomes a single-step dense predictor through lightweight adaptation. Training takes less than a week on one 32 GB GPU.

Marigold V2 🧐 Comfy Support designed by HUAWEI Bayer Lab for dense visual prediction, it takes a standard 2D image and calculates detailed, pixel-by-pixel convert into 3D structured data and surface properties. 👇

MARINO: U.S. MUST BE PREPARED TO “FIGHT MULTIPLE WARS” Marino says concerns over weapons stockpiles underscore the need to expand domestic production and secure critical supply chains: “The more of it that we can bring into the United States… the better.”