From word models to world models: Translating from natural language to the probabilistic language of thought
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 …
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
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 …
expecting that their actions or goals will disambiguate their intentions. How can we build …
[PDF][PDF] Probabilistic programming versus meta-learning as models of cognition
DC Ong, T Zhi-Xuan… - … and brain sciences, 2024 - cascoglab.psy.utexas.edu
We summarize the recent progress made by probabilistic programming as a unifying
formalism for the probabilistic, symbolic, and data-driven aspects of human cognition. We …
formalism for the probabilistic, symbolic, and data-driven aspects of human cognition. We …
Infinite ends from finite samples: Open-ended goal inference as top-down Bayesian filtering of bottom-up proposals
T Zhi-Xuan, G Kang, V Mansinghka… - arXiv preprint arXiv …, 2024 - arxiv.org
The space of human goals is tremendously vast; and yet, from just a few moments of
watching a scene or reading a story, we seem to spontaneously infer a range of plausible …
watching a scene or reading a story, we seem to spontaneously infer a range of plausible …
Report of the First ONTOX stakeholder network meeting: Digging under the surface of ONTOX together with the stakeholders
MG Diemar, M Vinken, M Teunis… - Alternatives to …, 2024 - journals.sagepub.com
The first Stakeholder Network Meeting of the EU Horizon 2020-funded ONTOX project was
held on 13–14 March 2023, in Brussels, Belgium. The discussion centred around identifying …
held on 13–14 March 2023, in Brussels, Belgium. The discussion centred around identifying …
Understanding Epistemic Language with a Bayesian Theory of Mind
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 …
beliefs cannot be directly observed? In this paper, we introduce a cognitive model of …
Bayes3D: fast learning and inference in structured generative models of 3D objects and scenes
Robots cannot yet match humans' ability to rapidly learn the shapes of novel 3D objects and
recognize them robustly despite clutter and occlusion. We present Bayes3D, an uncertainty …
recognize them robustly despite clutter and occlusion. We present Bayes3D, an uncertainty …
Suspension Analysis and Selective Continuation-Passing Style for Universal Probabilistic Programming Languages
Universal probabilistic programming languages (PPLs) make it relatively easy to encode
and automatically solve statistical inference problems. To solve inference problems, PPL …
and automatically solve statistical inference problems. To solve inference problems, PPL …
Partially Observable Task and Motion Planning with Uncertainty and Risk Awareness
Integrated task and motion planning (TAMP) has proven to be a valuable approach to
generalizable long-horizon robotic manipulation and navigation problems. However, the …
generalizable long-horizon robotic manipulation and navigation problems. However, the …
Score-Based Metropolis-Hastings Algorithms
In this paper, we introduce a new approach for integrating score-based models with the
Metropolis-Hastings algorithm. While traditional score-based diffusion models excel in …
Metropolis-Hastings algorithm. While traditional score-based diffusion models excel in …