标签
本文介绍了Embed-TTT,一种两步式测试时训练协议,通过首先微调任务嵌入,然后微调骨干网络,来改进类ARC任务中的规则归纳,从而更好地与底层规则对齐,并在ARC-AGI-1和ConceptARC等基准测试上提升性能。
本文通过扩展认知科学中的规则归纳任务,评估推理模型是否表现出系统性,发现模型在解决单个任务后,常在结构等价变体上失败,这表明其推理能力缺乏系统性。
Introduces LiFTER, a neuro-symbolic predictor for continuous-time dynamic graph forecasting that grounds predictions in observable temporal facts and executable rules, enabling fully inspectable and verifiable link prediction with competitive accuracy and high explanatory fidelity.