🔢 Scientific Computing

Mankirat47/Dao-Heart-v3.14: Dao Heart v3.14 : a bounded symbolic AI value governance research scaffold for studying value drift, oversight, warmth preservation, and identity stability under pressure.

🐙Open Source Code

github.com··Hacker News

Fourier fractal dimension to predict the generalization of deep neural networks

🧠Machine Learning Academic

arxiv.org·

Function-Space Priors for Bayesian Neural ODEs with Application to Vessel Trajectory Prediction

📐Estimation Theory Academic

arxiv.org·

mingusb/transformer-golf: The Fully Unrolled Transformer: An experimental repository for architecture simplification and compilation. [2026]

🤖Transformers Code

github.com··Hacker News

Neural Galerkin Normalizing Flows for Bayesian Inference of Diffusions with Inaccessible Boundaries

🎲Stochastic Processes Academic

arxiv.org·

The Right Measure for Physics-Constrained Generation: A Co-Area Correction for Posterior-Consistent PDE Inverse Problems

🌀Riemannian Optimization Academic

arxiv.org·

Effective Dimensionality as an Operator Invariant for Physics-Preserving Constraint Adaptation in Physics-Informed Neural Networks

📐Estimation Theory Academic

arxiv.org·

3D Underwater Path Planning via Generative Flow Field Surrogates

🤖Robotics Academic

arxiv.org·

SAT-Physical Thermodynamic Framework: treating constraints as a thermal system

🔢SciPy Code

github.com··Hacker News

Learning from Demonstrations over Riemannian Manifolds using Neural ODEs: An Extended Abstract

🌀Riemannian Optimization Academic

arxiv.org·

Less-relevant results

Mankirat47/Dao-Heart-3.13: An inspectable, symbolic value governance layer for AI, simulate then commit guards for warmth, agency, identity, and honesty, with falsifiable benchmarks.

🔢SciPy Code

github.com··Hacker News

Show HN: One-Shot Program Generation Through Direct Memory Diffusion

🔢SciPy Code

github.com··Hacker News

From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous Environments

🎮Reinforcement Learning Academic

arxiv.org·

Alradyin/wallie-V2: AI VTuber / streamer framework with real-time vision, personality engine, and lip-synced avatar — built for Twitch, YouTube, and Kick.

✍️Prompt Engineering Code

github.com··Hacker News

joshcarter/claude-o-meter: Keep your Claude use at the redline or you're just giving Anthropic free money

🔢SciPy Code

github.com··Hacker News

IBL-tools/rawtohdri: rawtohdri Converts bracketed camera raw files directly to an OpenEXR format HDRI.

🐙Open Source Code

github.com··Hacker News

No more posts from yfff's subscribed feeds.

Scour all 25257 feeds Learn more about Feeds

Curvature-aware dynamic precision approach for physics-informed neural networks

Operator learning for solving Fokker-Planck equations with various initial conditions

Policy Gradient for Continuous-Time Robust Markov Decision Processes

Mankirat47/Dao-Heart-v3.14: Dao Heart v3.14 : a bounded symbolic AI value governance research scaffold for studying value drift, oversight, warmth preservation, and identity stability under pressure.

Fourier fractal dimension to predict the generalization of deep neural networks

Function-Space Priors for Bayesian Neural ODEs with Application to Vessel Trajectory Prediction

mingusb/transformer-golf: The Fully Unrolled Transformer: An experimental repository for architecture simplification and compilation. [2026]

Neural Galerkin Normalizing Flows for Bayesian Inference of Diffusions with Inaccessible Boundaries

The Right Measure for Physics-Constrained Generation: A Co-Area Correction for Posterior-Consistent PDE Inverse Problems

Effective Dimensionality as an Operator Invariant for Physics-Preserving Constraint Adaptation in Physics-Informed Neural Networks

3D Underwater Path Planning via Generative Flow Field Surrogates

SAT-Physical Thermodynamic Framework: treating constraints as a thermal system

Learning from Demonstrations over Riemannian Manifolds using Neural ODEs: An Extended Abstract

Mankirat47/Dao-Heart-3.13: An inspectable, symbolic value governance layer for AI, simulate then commit guards for warmth, agency, identity, and honesty, with falsifiable benchmarks.

Show HN: One-Shot Program Generation Through Direct Memory Diffusion

From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous Environments

Alradyin/wallie-V2: AI VTuber / streamer framework with real-time vision, personality engine, and lip-synced avatar — built for Twitch, YouTube, and Kick.

joshcarter/claude-o-meter: Keep your Claude use at the redline or you're just giving Anthropic free money

IBL-tools/rawtohdri: rawtohdri Converts bracketed camera raw files directly to an OpenEXR format HDRI.