







Blue noise point sets are both hyperuniform (large-scale density fluctuations suppressed) and disordered, filling space evenly without introducing regular patterns. This makes them perceptually favorable, well suited to numerical integration, and effective for aliasing-free sampling. We borrow insights from the study of hyperuniform point sets in condensed matter physics and show that optimizing the disordered ground states of stealthy potentials yields blue noise that saturates the spectral-gap limit. Such point sets can be obtained by plain gradient descent, without early stopping. Using bond-orientational order parameters from the study of 2D melting, we map the Pareto frontier between uniformity and disorder, giving a real-space characterization that complements the standard spectral view of blue noise. We extend the method to non-Euclidean manifolds, combine stealthy losses over unions of point sets to construct multi-class blue noise that enables runtime-adjustable variable-density sampling, and apply reprojective constraints so that such point sets can be stored as textures. Finally, we generalize the loss from suppressing Fourier modes to matching arbitrary spectral targets, and introduce a spatially-varying frequency budget that scales each point's constrained modes by local density, enabling stippling that maintains consistent visual quality at all densities without crystallization artifacts.
Non-equilibrium active noise enhances generative memory in diffusion models
Generative diffusion models have emerged as powerful tools for sampling high-dimensional distributions, yet they typically rely on white gaussian noise and noise schedules to destroy and reconstruct information. Here, we demonstrate that driving the generative process out of equilibrium using active, temporally correlated noise sources fundamentally alters the information thermodynamics of the system. We show that coupling the data to an active non-Markovian bath creates a `memory effect' where high-level semantic information (such as class identity or molecular metastability) is stored in the temporal correlations of auxiliary degrees of freedom. Using Fisher information analysis, we prove that this active mechanism significantly retards the rate of information decay compared to passive Brownian motion. Crucially, this memory effect facilitates an earlier and more robust symmetry breaking (speciation) during the reverse generative process, allowing the system to resolve multi-scale structures, reminiscent of metastable states in molecular configurations that are washed out in the typical noising processes. Our results suggest that non-equilibrium protocols, inspired by active matter physics, offer a thermodynamically distinct and potentially advantageous pathway for recovering high-dimensional energy landscapes using generative diffusion.

Evaluating and Sampling Glinty NDFs in Constant Time
Geometric features between the micro and macro scales produce an expressive family of visual effects grouped under the term 'glints'. Efficiently rendering these effects amounts to finding the highlights caused by the geometry under each pixel. To allow for fast rendering, we represent our faceted geometry as a 4D point process on an implicit multiscale grid, designed to efficiently find the facets most likely to cause a highlight. The facets' normals are generated to match a given micro-facet normal distribution such as Trowbridge-Reitz (GGX) or Beckmann, to which our model converges under increasing surface area. Our method is simple to implement, memory-and-precomputation-free, allows for importance sampling and covers a wide range of different appearances such as anisotropic as well as individually colored particles. We provide a base implementation as a standalone fragment shader.
Generating Blue Noise Textures With Void And Cluster
Blue noise comes in two main flavors: sample points and masks. I’ll be calling blue noise masks “blue noise textures” in this post. The code that accompanies this post, implementi…

Nicole Feng
We introduce a method for approximating the signed distance function (SDF) of geometry corrupted by holes, noise, or self-intersections. The method implicitly defines a completed version of the shape, rather than explicitly repairing the given input. Our starting point is a modified version of the heat method for geodesic distance, which diffuses normal vectors rather than a scalar distribution. This formulation provides robustness akin to generalized winding numbers (GWN), but provides distance function rather than just an inside/outside classification. Our formulation also offers several features not common to classic distance algorithms, such as the ability to simultaneously fit multiple level sets, a notion of distance for geometry that does not topologically bound any region, and the ability to mix and match signed and unsigned distance. The method can be applied in any dimension and to any spatial discretization, including triangle meshes, tet meshes, point clouds, polygonal meshes, voxelized surfaces, and regular grids. We evaluate the method on several challenging examples, implementing normal offsets and other morphological operations directly on imperfect curve and surface data. In many cases we also obtain an inside/outside classification dramatically more robust than the one obtained provided by GWN.
FarbVélo —— Random Color Cycler
Generative color harmonies. The random color explorer

Dataset Condensation with Distribution Matching
Computational cost to train state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising direction to reduce training time is dataset condensation that aims to replace the original large training set with a significantly smaller learned synthetic set while preserving its information. While training deep models on the small set of condensed images can be extremely fast, their synthesis remains computationally expensive due to the complex bi-level optimization and second-order derivative computation. In this work, we propose a simple yet effective dataset condensation technique that requires significantly lower training cost with comparable performance by matching feature distributions of the synthetic and original training images in sampled embedding spaces. Thanks to its efficiency, we apply our method to more realistic and larger datasets with sophisticated neural architectures and achieve a significant performance boost while using larger synthetic training set. We also show various practical benefits of our method in continual learning and neural architecture search.
A Journey Into Shaders
Demystify shaders with this beginner-friendly guide. Explore fragment shaders, signed distance functions, and metaballs through interactive code examples. Learn how to create beautiful blob animations and effects using just a few lines of code.

Nicole Feng
We describe a method for computing signed distance to point clouds that allows fast pointwise evaluation at arbitrary spatial resolution. As input, our method takes a point cloud with normals; as output, it provides an analytical parameterization that allows queries of signed distance to the approximate underlying surface at arbitrary points — simultaneously providing reconstruction and distance. Our key idea is to reconstruct shapes by locally fitting point clouds with tori, which have closed-form signed distance functions. Tori are fitted in a feed-forward manner, using a pre-trained network to output per-point curvature and shift parameters. Importantly, our method does not require costly global optimization or spatial discretization, and is easily parallelizable. Underlying our method is a new theory that unifies signed distance with the classic reconstruction methods of winding numbers and Poisson surface reconstruction. We use our method to compute signed distance to point clouds arising from photogrammetry, meshes, 3D Gaussians, and neural implicits. Our method allows point clouds to be used directly in applications, without explicit surface reconstruction: as examples, we take offsets of point clouds, apply morphological and Boolean operations, and directly visualize offset surfaces using sphere tracing.
Tethered Reasoning: Decoupling Entropy from Hallucination in Quantized LLMs via Manifold Steering
A fundamental challenge in quantized inference is the temperature-entropy trade-off: low sampling temperatures yield repetitive, mode-collapsed outputs, while high temperatures (T>2.0T{>}2.0) cause what is conventionally termed “hallucination”—semantic incoherence and factual errors. Quantization exacerbates this: 4-bit models exhibit earlier collapse than full-precision counterparts [5, 6]. Most inference frameworks cap temperature at T=2.0T{=}2.0, treating high-entropy regimes as inherently unstable.
SuGaR
SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering.
Discontinuity-Aware 2D Neural Fields
Neural image representations offer the possibility of high fidelity, compact storage, and resolution-independent accuracy, providing an attractive alternative to traditional pixel- and grid-based representations. However, coordinate neural networks fail to capture discontinuities present in the image and tend to blur across them; we aim to address this challenge. In many cases, such as rendered images, vector graphics, diffusion curves, or solutions to partial differential equations, the locations of the discontinuities are known. We take those locations as input, represented as linear, quadratic, or cubic \bez curves, and construct a feature field that is discontinuous across these locations and smooth everywhere else. Finally, we use a shallow multi-layer perceptron to decode the features into the signal value. To construct the feature field, we develop a new data structure based on a curved triangular mesh, with features stored on the vertices and on a subset of the edges that are marked as discontinuous. We show that our method can be used to compress a 100,000^2-pixel rendered image into a 25MB file; can be used as a new diffusion-curve solver by combining with Monte-Carlo-based methods or directly supervised by the diffusion-curve energy; or can be used for compressing 2D physics simulation data.
Single photon isolation and nonreciprocal frequency conversion in atom-waveguide systems
In this work, we utilize a two-level atom and a $Λ$-type atom to link two identical waveguides, subsequently extending the model to a giant-atom configuration. Our analytical solutions and numerical simulations demonstrate that this setup can achieve single-photon isolation and nonreciprocal frequency conversion by tuning the atom-waveguide coupling strengths $g_i$, respectively. We also examine single-photon scattering in the giant-atom model within both the Markovian and non-Markovian regimes. The results reveal that ultranarrow scattering windows are induced by the phases $φ_1$ and $φ_2$ under specific conditions, making them well-suited for precise frequency conversion and sensing. Additionally, in the non-Markovian regime, the spectra exhibit irregular polygonal shapes, offering enhanced opportunities for exploring nonreciprocal frequency conversion in the off-resonant regime. Our work provides a new perspective on achieving optical nonreciprocity at the single-photon level in atom-waveguide systems.

Shades of Halftone - The Blog of Maxime Heckel
An interactive deep dive into building halftone shaders in GLSL, covering everything from classic dot patterns and CMYK color separation to Moiré interference, gooey effects, and animated displacement.

Stylized Shader Breakdown - Blender 3D
Hash Functions for GPU Rendering – Nathan Reed’s coding blog
Pixels and polygons and shaders, oh my!