AI Engineering & Applied Research | LLMs, AI Evaluation & Verification | AI Systems Strategy
Highlights
- Pro
Pinned Loading
-
groundlens-dev/groundlens
groundlens-dev/groundlens PublicGuardrails for LLM answers. GroundLens checks an LLM answer against its sources without a model, decides PASS, REVIEW or FAIL under your policy, and keeps a signed record.
-
otwin-core/otwin-hybrid
otwin-core/otwin-hybrid PublicIn this repo we will show how to build a simple but useful Digital Twin using python. Our asset will be a Li-ion battery. This Digital Twin will allow us to model and predict batteries behavior and…
-
Geometric-Analysis-of-Reasoning-Trajectories-in-LLMs
Geometric-Analysis-of-Reasoning-Trajectories-in-LLMs PublicCode for the paper "Geometric Analysis of Reasoning Trajectories: A Phase Space Approach to Understanding Valid and Invalid Multi-Hop Reasoning in LLMs" (NeurReps, NeurIPS 2026 workshop)
Jupyter Notebook 4
-
Hamiltonian-Neural-Network-Optimization
Hamiltonian-Neural-Network-Optimization PublicBuilt on peer-reviewed research accepted at IEEE DSA 2025: "Hamiltonian Neural Networks for Robust Out-of-Time Credit Scoring: Empirical Validation and Temporal Stability Analysis"
Jupyter Notebook 1
-
Perplexity-Based-Adjacency-for-Uncertainty-Quantification
Perplexity-Based-Adjacency-for-Uncertainty-Quantification PublicThis repository contains experimental validation of the PBA (Perplexity-Based Adjacency) uncertainty quantification method for Large Language Models, as described in the paper "Perplexity-Based Adj…
Python 1
If the problem persists, check the GitHub status page or contact support.




