Building machines that learn and think with people

KM Collins, I Sucholutsky, U Bhatt, K Chandra… - Nature human …, 2024 - nature.com
What do we want from machine intelligence? We envision machines that are not just tools
for thought but partners in thought: reasonable, insightful, knowledgeable, reliable and …

From word models to world models: Translating from natural language to the probabilistic language of thought

L Wong, G Grand, AK Lew, ND Goodman… - arxiv preprint arxiv …, 2023 - arxiv.org
How does language inform our downstream thinking? In particular, how do humans make
meaning from language--and how can we leverage a theory of linguistic meaning to build …

Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning

T Zhi-Xuan, L Ying, V Mansinghka… - arxiv preprint arxiv …, 2024 - arxiv.org
People often give instructions whose meaning is ambiguous without further context,
expecting that their actions or goals will disambiguate their intentions. How can we build …

When robots get chatty: Grounding multimodal human-robot conversation and collaboration

P Allgeuer, H Ali, S Wermter - International Conference on Artificial Neural …, 2024 - Springer
We investigate the use of Large Language Models (LLMs) to equip neural robotic agents
with human-like social and cognitive competencies, for the purpose of open-ended human …

Inferring the goals of communicating agents from actions and instructions

L Ying, T Zhi-Xuan, V Mansinghka… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
When humans cooperate, they frequently coordinate their activity through both verbal
communication and non-verbal actions, using this information to infer a shared goal and …

Grounding Language about Belief in a Bayesian Theory-of-Mind

L Ying, T Zhi-Xuan, L Wong, V Mansinghka… - arxiv preprint arxiv …, 2024 - arxiv.org
Despite the fact that beliefs are mental states that cannot be directly observed, humans talk
about each others' beliefs on a regular basis, often using rich compositional language to …

Understanding Epistemic Language with a Bayesian Theory of Mind

L Ying, T Zhi-Xuan, L Wong, V Mansinghka… - arxiv preprint arxiv …, 2024 - arxiv.org
How do people understand and evaluate claims about others' beliefs, even though these
beliefs cannot be directly observed? In this paper, we introduce a cognitive model of …

GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignment

L Ying, K Jha, S Aarya, JB Tenenbaum… - arxiv preprint arxiv …, 2024 - arxiv.org
Verbal communication plays a crucial role in human cooperation, particularly when the
partners only have incomplete information about the task, environment, and each other's …

Neuro-Symbolic AI: Explainability, Challenges, and Future Trends

X Zhang, VS Sheng - arxiv preprint arxiv:2411.04383, 2024 - arxiv.org
Explainability is an essential reason limiting the application of neural networks in many vital
fields. Although neuro-symbolic AI hopes to enhance the overall explainability by leveraging …

Bridging the Gap: Representation Spaces in Neuro-Symbolic AI

X Zhang, VS Sheng - arxiv preprint arxiv:2411.04393, 2024 - arxiv.org
Neuro-symbolic AI is an effective method for improving the overall performance of AI models
by combining the advantages of neural networks and symbolic learning. However, there are …