asked claude fable 5 to design a 16dof articulated robot hand it also wrote a robot description file (urdf) for the hand ~ 1 hour / 300k tokens

🛫 A complete Airbus-class turbofan — fully parametric, animated, built entirely in the browser. Created in confBuild with Claude Fable 5: ⚙️ Real internals — 7-stage compressor, annular combustor, 4 turbine stages 🌀 Two-spool animation: HP & LP shafts at real differential speed 🔥 Flow lines & exhaust react live to the N1 lever 📐 Dimensions on sliders — everything recalculates exactly 📄 Export to STEP, auto-generate technical drawings Every chamfer and bore: calculated, not painted. #CAD #Engineering #Turbofan #Aerospace #confBuild #AI

Story-to-Motion: Synthesizing Infinite and Controllable Character Animation from Long Text Outperforms previous SotA motion synthesis methods across the board proj: story2motion.github.io/ abs: arxiv.org/abs/2311.07446

Video: youtu.be/EoAm1yZR-ao

RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation paper page: huggingface.co/papers/2311.0… present RoboGen, a generative robotic agent that automatically learns diverse robotic skills at scale via generative simulation. RoboGen leverages the latest advancements in foundation and generative models. Instead of directly using or adapting these models to produce policies or low-level actions, we advocate for a generative scheme, which uses these models to automatically generate diversified tasks, scenes, and training supervisions, thereby scaling up robotic skill learning with minimal human supervision. Our approach equips a robotic agent with a self-guided propose-generate-learn cycle: the agent first proposes interesting tasks and skills to develop, and then generates corresponding simulation environments by populating pertinent objects and assets with proper spatial configurations. Afterwards, the agent decomposes the proposed high-level task into sub-tasks, selects the optimal learning approach (reinforcement learning, motion planning, or trajectory optimization), generates required training supervision, and then learns policies to acquire the proposed skill. Our work attempts to extract the extensive and versatile knowledge embedded in large-scale models and transfer them to the field of robotics. Our fully generative pipeline can be queried repeatedly, producing an endless stream of skill demonstrations associated with diverse tasks and environments.

AIのおかげで今や論文を読むことは一般人にとっても驚くほど簡単なことになった。

LLMにまず前提から尋ることで出力精度を向上させる『ステップバック・プロンプティング』と実行プロンプト aiboom.net/archives/56671 DeepMindによる研究報告の解説記事です。 シンプルながら確かな性能を持つテクニックに目から鱗な方も多かった様子。 具体的な対話例などを掲載しました。

This is a game changer. You can use ChatGPT to transform equations to python functions. Wish I had this 5 years ago.

DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation paper page: huggingface.co/papers/2309.1… Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been exhibited, these methods often suffer from slow per-sample optimization, limiting their practical usage. In this paper, we propose DreamGaussian, a novel 3D content generation framework that achieves both efficiency and quality simultaneously. Our key insight is to design a generative 3D Gaussian Splatting model with companioned mesh extraction and texture refinement in UV space. In contrast to the occupancy pruning used in Neural Radiance Fields, we demonstrate that the progressive densification of 3D Gaussians converges significantly faster for 3D generative tasks. To further enhance the texture quality and facilitate downstream applications, we introduce an efficient algorithm to convert 3D Gaussians into textured meshes and apply a fine-tuning stage to refine the details. Extensive experiments demonstrate the superior efficiency and competitive generation quality of our proposed approach. Notably, DreamGaussian produces high-quality textured meshes in just 2 minutes from a single-view image, achieving approximately 10 times acceleration compared to existing methods.

Do language models have an internal world model? A sense of time? At multiple spatiotemporal scales? In a new paper with @tegmark we provide evidence that they do by finding a literal map of the world inside the activations of Llama-2!