PDEFlow: Streamlining Solver-Backed Neural Operators
PDEFlow offers a novel framework for translating ODE and PDE descriptions into neural-operator pipelines, minimizing manual intervention in scientific workflows.
Read the full articleYou might also wanna read
Topological Neural Operators [deep math version]
Authors: Lennart Bastian, Samuel Leventhal, Mustafa Hajij, Tolga Birdal
arxiviq.substack.com·21d ago
Program-as-Weights: Compiling Natural-Language Specifications into Compact, Locally-Executable Neural Programs
Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, o
arxiv.org·8d agoBreaking Quadratic Barriers: A Non-Attention LLM for Ultra-Long Context Horizons
Article URL: Comments URL: Points: 11 # Comments: 1
arxiv.org·1y ago
GPEmu: A GPU Emulator for Rapid, Low-Cost Deep Learning Prototyping [pdf]
Article URL: Comments URL: Points: 3 # Comments: 0
vldb.org·1y ago
mytorch: Python Automatic Differentiation Library Inspired by PyTorch
Automatic differentiation implemented in python, inspired by Pytorch (easily extensible) - obround/mytorch
github.com·6mo agoParcae: Doing more with fewer parameters using stable looped models
Parcae is a stable looped language model that matches the quality of a Transformer twice its size — a 770M model reaching 1.3B-level perform
Together·2mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.