@Q-Shadow

Upstream open-source contributions to foundational machine learning libraries and deep-tech ecosystems (including PyTorch, TensorFlow, and AMD ROCm). When hitting development walls or boredom during local AI modeling, I actively transition to diagnosing issue trackers, tracking framework bugs, writing optimization patches, and submitting Pull Requests directly to major AI infrastructure repos to support the global developer stack.

Kinetic-AG A research prototype for model-guided visual-spatial reasoning with deterministic grid operations. Kinetic-AG explores a neuro-symbolic approach to ARC-style puzzles and related visual tasks. An AI model is intended to propose symbolic operations; K-VL, the Kinetic Visual Language library, applies those operations to discrete grids with explicit, testable semantics.