Paper collection on building and evaluating language model agents via executable language grounding
Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.
[ICML 2025] Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale
A curated paper list on neural symbolic and probabilistic logic.
mOWL: Machine Learning library with Ontologies
AIKA (Artificial Intelligence for Knowledge Acquisition) is an innovative approach to neural network design, diverging from traditional architectures that rely heavily on rigid matrix and vector operations. The AIKA Project introduces a flexible, sparse, and non-layered network representation, derived from a type hierarchy.
Neural-Grammar-Symbolic Learning with Back-Search
Explainable complex question answering over RDF files via Llama Index.
OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System.
一项致力于通过神经符号与沙盒审计自演进重构通用智能底层逻辑的前沿探索
LAAP AGI - Zero-LLM Cognitive Architecture for Digital Lifeforms. Rust PSI core at 2000Hz, QRE quantum reasoning, EpisodicMemory, RulesEngine. 25+ modules, all local inference.打造新一代agent数字生命体框架底座，赋予具身智能，编程智能体真正的数字生命感
Symbolic DNN-Tuner is a system to drive the training of a Deep Neural Network, analysing the performance of each training experiment and automatizing the choice of HPs to obtain a network with better performance.
Holographic Memory for zero-shot compositional KG reasoning. Real HRR & Complex FHRR with Hopfield cleanup on FB15k-237 (5 seeds). Both fail at composition – the mechanism is phase decorrelation, not modulus collapse.
Implementation of a new scenario for the Neural-Symbolic system NEUROLOG
NeuroLog: A Neural-Symbolic System
Jupyter notebooks with examples of Logical Neural Networks (LNN) by IBM
Neural-Symbolic-Superintelligence scaling
KERNEL Ω est une architecture cognitive unifiée pour LLMs. En fusionnant Graph of Thoughts, Self-Discover et Few-Shot Introspectif, il transforme les générateurs de texte linéaires en moteurs d'inférence réflexifs capables de douter, de s'auto-corriger et de cartographier leur propre pensée.
A Neural-Symbolic Causal Knowledge Tracing system for multimodal agentic grading and diagnostic feedback
To associate your repository with the neural-symbolic topic, visit your repo's landing page and select "manage topics."