Tag
This paper presents a general neurosymbolic reasoning and learning methodology that modularly integrates Answer Set Programming with an Energy Based Model substrate, supporting joint optimization in continuous latent space and end-to-end training. It demonstrates applications on MNIST, CLEVR, and MOT benchmarks.
Forethought is a neurosymbolic reasoning system that treats reasoning as an explicit, verifiable program composed from symbolic and neural primitives. It improves base-model accuracy by about 30% relative and enables small models to match frontier models while being model-agnostic and auditable.
This paper introduces NeSyCat Torch, a differentiable tensor implementation of categorical semantics for neurosymbolic learning, unifying classical, fuzzy, and probabilistic semantics under a monadic framework and demonstrating superior speed and accuracy on MNIST addition compared to existing systems like LTN and DeepProbLog.
Introduces a neurosymbolic framework that injects LTLf constraints into transformer-based reinforcement learning policies via differentiable automaton representations and a logic-based loss, improving constraint satisfaction while maintaining competitive returns.
This paper introduces A4D, a framework that maps visual observations into a shared latent space structured around affordances (e.g., 'movable') for robot planning. It achieves 94% inference accuracy on existing affordances, outperforming state-of-the-art by 15%, and enables 100x faster inference with superior generalization to unseen object functionalities.
This paper presents a method for distilling answer-set programming rules from large language models to enhance neurosymbolic visual question answering, showing that only a few examples are needed to generate correct rules.
This paper proposes Geodesic Flow Matching, a Riemannian transport method for denoising Spatial Semantic Pointers (SSPs) on toroidal manifolds, and demonstrates a 72% reduction in tracking error and 40% efficiency gain in a spiking neural SLAM system.
ImProver 2 is a neurosymbolic framework for automated proof optimization in Lean 4 that uses an expert-iteration pipeline and a scaffold to train a 7B-parameter model, outperforming much larger models and demonstrating that small models can effectively restructure research-level proofs.
NeuroNL2LTL is a neurosymbolic framework that translates natural language to Linear Temporal Logic (LTL) using a two-stage architecture with verifier-in-the-loop training, achieving improved correctness guarantees for safety-critical specifications.
This paper introduces novel methods for generating high-quality embeddings for Horn logic reasoning using triplet loss, including techniques for balanced training example generation and hard example emphasis, which improve the efficiency of downstream logical reasoning.
This paper introduces Constrained Diffusion for Code (CDC), a training-free neurosymbolic inference framework that integrates constraint satisfaction directly into the reverse denoising process of discrete diffusion models for code generation. CDC consistently improves constraint satisfaction in functional correctness, security, and syntax across benchmarks, outperforming existing diffusion and autoregressive baselines.