Find all the TopSymbolic and Logic-Based AI papers. Links to pdf, code repos and demos are provided.
Recent advances in theoretical biology suggest that basal cognition and sentient behaviour are emergent properties of in vitro cell cultures and neuro...
see more
Introduces START, a novel long chain-of-thought (CoT) reasoning model that integrates external tools, specifically a Python interpreter, to enhance re...
see more
Introduces Spatial Reasoning Models (SRMs), a framework utilizing denoising generative models for reasoning over continuous variables in spatial domai...
see more
Reviews the need for a unified cell ontology within the context of the Human Cell Atlas initiative, addressing the complexities arising from massive s...
see more
Addresses the challenge of finding equilibria in polymatrix games while maintaining differentially private guarantees. It demonstrates that high accur...
see more
Introduces SWE-RL, a reinforcement learning approach designed to enhance large language models (LLMs) for real-world software engineering tasks using ...
see more
Investigates the relationship between causality, symmetry, and data compression, proposing a framework where causality emerges through data compressio...
see more
Introduces TRANSIT, a new model for creating background data templates for weakly-supervised anomaly searches at the LHC, utilizing a transport advers...
see more
The International AI Safety Report synthesizes current evidence on the capabilities, risks, and safety of advanced general-purpose AI systems, drawing...
see more
Introduces CASTLE, a benchmarking framework designed to evaluate the vulnerability detection capabilities of static code analyzers, formal verificatio...
see more
We advance the recently proposed neuro-symbolic Differentiable Tree Machine, which learns tree operations using a combination of transformers and Tens...
see more
Understanding commonsense causality is a unique mark of intelligence for humans. It helps people understand the principles of the real world better an...
see more
