Evolving Minds: Logic-Informed Inference from Temporal Action Patterns
Chao Yang, Shuting Cui, Yang Yang, Shuang Li
Abstract
Understanding human mental states-such as intentions and desires-is crucial for natural AIhuman collaboration. However, this is challenging because human actions occur irregularly over time, and the underlying mental states that drive these actions are unobserved. To tackle this, we propose a novel framework that combines a logicinformed temporal point process (TPP) with amortized variational Expectation-Maximization (EM).
Our key innovation is integrating logic rules as priors to guide the TPP's intensity function, allowing the model to capture the interplay between actions and mental events while reducing dependence on large datasets. To handle the intractability of mental state inference, we introduce a discrete-time renewal process to approximate the posterior. By jointly optimizing model parameters, logic rules, and inference networks, our approach infers entire mental event sequences and adaptively predicts future actions. Experiments on both synthetic and real-world datasets show that our method outperforms existing approaches in accurately inferring mental states and predicting actions, demonstrating its effectiveness in modeling human cognitive processes.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Branching Diffusion for Point Processes in Time and Space cites Transformer Hawkes Process
- Forward-Chaining Temporal Point Process cites Transformer Hawkes Process
- Transformer Embeddings of Irregularly Spaced Events and Their Participants cites Transformer Hawkes Process
- Transformer Embeddings of Irregularly Spaced Events and Their Participants cites Self-Attentive Hawkes Process
Cited by top-tier papers3
Builds on15
- Transformer Hawkes ProcessSimiao Zuo, Haoming Jiang, Zichong Li, Tuo Zhao et al.ICML 2020 · 382 citations
- Self-Attentive Hawkes ProcessQiang Zhang, Aldo Lipani, Ömer Kirnap, Emine YilmazICML 2020 · 254 citations
- Collaborating with Humans without Human DataDJ Strouse, Kevin R. McKee, Matt M. Botvinick, Edward Hughes et al.NeurIPS 2021 · 239 citations
- Watch-And-Help: A Challenge for Social Perception and Human-AI CollaborationXavier Puig, Tianmin Shu, Shuang Li, Zilin Wang et al.ICLR 2021 · 170 citations
- Transformer Embeddings of Irregularly Spaced Events and Their ParticipantsHongyuan Mei, Chenghao Yang, Jason EisnerICLR 2022 · 98 citations
Related papers
- Enhancing Human-AI Collaboration Through Logic-Guided ReasoningChengzhi Cao, Yinghao Fu, Sheng Xu, Ruimao Zhang et al.ICLR 2024 · 7 citations
- Latent Logic Tree Extraction for Event Sequence Explanation from LLMsZitao Song, Chao Yang, Chaojie Wang, Bo An et al.ICML 2024 · 11 citations
- Discovering Intrinsic Spatial-Temporal Logic Rules to Explain Human ActionsChengzhi Cao, Chao Yang, Ruimao Zhang, Shuang LiNeurIPS 2023 · 7 citations
- Explaining Point Processes by Learning Interpretable Temporal Logic RulesShuang Li, Mingquan Feng, Lu Wang, Abdelmajid Essofi et al.ICLR 2022 · 21 citations
- Temporal Logic Point ProcessesShuang Li, Lu Wang, Ruizhi Zhang, Xiaofu Chang et al.ICML 2020 · 22 citations
