At the Trustworthy Knowledge-Driven Artificial Intelligence (TKAI) Lab, we combine research ideas derived from formal methods, linguistics, cognitive science, and machine learning to efficiently build intelligent systems that are trustworthy, ethical, and secure. These models should have properties such as robustness and interpretability, such that humans can easily understand the generated information. This would mean designing agents that are expected to learn desirable behavior with minimal supervision/data that are provably stable and generalize to unseen distributions. We believe these objectives can be stably achieved by designing knowledge-guided neuro-symbolic agents.
TKAI Lab
Trustworthy Knowledge-Driven Artificial Intelligence (TKAI) Lab
- 5 followers
- United States of America
- https://tkai-lab-mali.github.io/
Popular repositories Loading
-
NeuroSymbolicLM
NeuroSymbolicLM PublicNeuro-Symbollic LM with Automaton-Augmented Retrieval for Generalization through Memorization on TriviaQA
Python 1
-
Curvature-Weighted-Capacity-Allocation
Curvature-Weighted-Capacity-Allocation PublicCodebase for the Curvature Weighted Capacity Allocation paper
HTML 1
-
-
-
pinns-torch
pinns-torch PublicForked from rezaakb/pinns-torch
PINNs-Torch, Physics-informed Neural Networks (PINNs) implemented in PyTorch.
Python
Repositories
Showing 7 of 7 repositories
- Curvature-Weighted-Capacity-Allocation Public
Codebase for the Curvature Weighted Capacity Allocation paper
- NeuroSymbolicLM Public
Neuro-Symbollic LM with Automaton-Augmented Retrieval for Generalization through Memorization on TriviaQA
- RPG Public Forked from complex-reasoning/RPG
[ICLR 2026] RPG: KL-Regularized Policy Gradient (https://arxiv.org/abs/2505.17508)
- RealKcat Public
- .github Public
- pinns-torch Public Forked from rezaakb/pinns-torch
PINNs-Torch, Physics-informed Neural Networks (PINNs) implemented in PyTorch.
Top languages
Loading…
Most used topics
Loading…