Project in collaboration with Vicki Li and Pawan Jayakumar for a Program Synthesis course at UCSD (taught by Loris D’Antoni).


<aside> 💡

We attempted to implement a neurosymbolic architecture to solve the ARC-AGI challenge by applying a lightweight (yet expressive) domain specific language (DSL) on the ‘object-level’ within ARC problems.

Several elements were successful — object-level segmentation, learning semantically meaningful object embeddings, generating synthetic data using our DSL, applying a graph-bijection solver — but our ultimate ambition fell short due to a key neural network in our proposed approach failing to learn non-trivial mappings.

📄 Formal write-up here.

</aside>

Visualization of attention logits from the class token in our embedding model.

Visualization of attention logits from the class token in our embedding model.

Problems we were able to solve with the naive graph bijection solver (that uses our object-specific DSL).

Problems we were able to solve with the naive graph bijection solver (that uses our object-specific DSL).

Approach

Object Segmentation

Domain Specific Language (DSL)

Synthetic Data Generation

ARC Object Embedding

Training the Probabilistic Grammar

Graph Bijection Solver

Takeaways