activity
20212026
most citedActive Preference Inference using Language Models and Probabilistic Reasoning

3 citations · 4 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CV2026

Bongards at the Boundary of Perception and Reasoning: Programs or Language?

Cassidy Langenfeld, Claas Beger, Gloria Geng +4

Vision-Language Models (VLMs) have made great strides in everyday visual tasks, such as captioning a natural image, or answering commonsense questions about such images. But humans…

cs.AI2025

PoE-World: Compositional World Modeling with Products of Programmatic Experts

Wasu Top Piriyakulkij, Yichao Liang, Hao Tang +3

Learning how the world works is central to building AI agents that can adapt to complex environments. Traditional world models based on deep learning demand vast amounts of trainin…

cs.AI2024

Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning

Wasu Top Piriyakulkij, Cassidy Langenfeld, Tuan Anh Le +1

We give a model of how to infer natural language rules by doing experiments. The model integrates Large Language Models (LLMs) with Monte Carlo algorithms for probabilistic inferen…

cs.LG2024★ 1 cited

Denoising Diffusion Variational Inference: Diffusion Models as Expressive Variational Posteriors

Wasu Top Piriyakulkij, Yingheng Wang, Volodymyr Kuleshov

We propose denoising diffusion variational inference (DDVI), a black-box variational inference algorithm for latent variable models which relies on diffusion models as flexible app…

cs.CL2023★ 3 cited

Active Preference Inference using Language Models and Probabilistic Reasoning

Wasu Top Piriyakulkij, Volodymyr Kuleshov, Kevin Ellis

Actively inferring user preferences, for example by asking good questions, is important for any human-facing decision-making system. Active inference allows such systems to adapt a…

cs.LG2021

TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary Data

Wasu Piriyakulkij, Cristina Menghini, Ross Briden +4

Machine learning practitioners often have access to a spectrum of data: labeled data for the target task (which is often limited), unlabeled data, and auxiliary data, the many avai…