Topics
Results for “neural networks”
33 results
- MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations — Hugging Face Papers · Seen · 32 points
- Astrocyte Biocomputing: Astrocytic Contributions to Neural Network Computation — arXiv AI Papers · Seen
- ERGo: Energy-Efficient Hybrid Graph Neural Network Training on Processing-In-Memory Architectures — arXiv AI Papers · Seen
- Physics2Weight: Direct Neural Network Architecture and Weight Generation from Physical Laws Using Large Language Models — arXiv AI Papers · Seen
- PINNeval: A Comprehensive Evaluation Standard for Physics-Informed Neural Networks — arXiv AI Papers · Seen
- Emergent Low-Dimensional Topological Dynamics Dictate Generalization and Escape Mechanics in Billion-Parameter Neural Networks — arXiv AI Papers · Seen
- Adaptive Depth Aggregation in Graph Transformers for Long-Range Graph Reasoning — arXiv AI Papers · Seen
- Generative Reconstruction of Full-Field Sensor States for Safety-Critical Digital Twins — arXiv AI Papers · Seen
- Embedding Consistent Recurrent Neural Networks in Finite Element Simulations for Path-Dependent Damage Prediction — arXiv AI Papers · Seen
- Stochastic Dynamics of Generative AI: From Autoregressive Models to Interacting LLM Networks and Neural SDEs — arXiv AI Papers · Seen
- Qwen 3.8 27B on my laptop can interpret model weights, too — Hacker News · Seen · 713 points
- Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights — 2 sources · Seen · 2,935 points
- Embedding boolean circuits in a neural network — Hacker News · Seen · 32 points
- LLMs are not superhuman at reading and writing neural network weights — Hacker News · Seen · 145 points
- AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn — arXiv AI Papers · Seen
- Show HN: I Turned DOOM into a Transformer — Hacker News · Seen · 129 points
- Learning Without Clocks: Partition-Invariant Neural Network — arXiv AI Papers · Seen
- The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network — arXiv AI Papers · Seen
- Incorporating graph neural network into route choice model — arXiv AI Papers · Seen
- Dynamical coarse-graining of neural-network training — arXiv AI Papers · Seen
- Scaling and Renormalization in Neural Networks: An Effective Renormalization-Group Description of Grokking — arXiv AI Papers · Seen
- Multiple Leak Localization in Water Distribution Networks through Graph Neural Networks — arXiv AI Papers · Seen
- Every Weight Is a Path of Shared Discrete Decisions — Hugging Face Papers · Seen · 23 points
- Attention Is Not What You Need — Hacker News · Seen · 190 points
- Towards Adversarially Robust Multigraph Neural Networks for Financial Crime Analysis — arXiv AI Papers · Seen
- Escaping the Phylogenetic Trap: Persistent Homology Enables Cross-Species Ion Channel Classification via Multimodal Graph Neural Networks — arXiv AI Papers · Seen
- Spike-Aware Gradient-Based Mixed-Precision Quantization of Spiking Neural Networks for Vision Applications — arXiv AI Papers · Seen
- Neural Networks with Differentiable Belief-Function Layers — arXiv AI Papers · Seen
- baseVultra: Compact Nonlinear Recurrence with Reallocated Capacity — arXiv AI Papers · Seen
- A General Topological Symmetry Index for Critical Orbits In Neural Network Loss Landscapes — arXiv AI Papers · Seen
- Scalable Stress-Constrained Topology Optimization: A Super-resolution and Simultaneous Approach Based on Machine Learning — arXiv AI Papers · Seen
- Rate as a Feature, Not a Nuisance: Curriculum FiLM Training for Event-Based Graph Neural Networks — arXiv AI Papers · Seen
- Neural networks are clean — 2 sources · Seen · 807 points