Tag
This paper proposes version-aware operations and transaction memories for the MeMo architecture, enabling direct editing of explicit correlation matrix memories instead of full retraining when knowledge changes.
This paper introduces a two-stage neuro-symbolic framework that uses weak supervision (as little as 1% labels) with a slot-based VAE to learn interpretable symbols for object-centric visual reasoning, outperforming foundation models in domain generalization.
This paper introduces a neuro-symbolic pipeline using 2.5-D decomposition to improve LLM-based spatial construction accuracy by offloading vertical coordinate calculation to a deterministic executor, achieving high accuracy on benchmarks and edge hardware.
This paper introduces SHARP, a neuro-symbolic framework for financial trading agents that uses structured, human-auditable rubrics for policy optimization to improve robustness and transparency in noisy market environments.