Scott Sanner

Associate Professor@Department of Mechanical and Industrial Engineering, University of Toronto·加拿大·OpenReview

研究方向

mdps · planning under uncertainty · decision-theoretic planning · graphical models · bayes nets · bayesian networks · exact inference · approximate inference · information retrieval · recommender systems

Scott Sanner

Improving Set Function Approximation with Quasi-Arithmetic Neural Networks

Structure-Aware Graph Hypernetworks for Neural Program Synthesis

Natural Language PDDL (NL-PDDL) for Open-world Goal-oriented Commonsense Regression Planning in Embodied AI

Agent-Chained Policy Optimization

ActiveVOO: Value of Observation Guided Active Knowledge Acquisition for Open-World Embodied Lifted Regression Planning

Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens

Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects

Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction

Open-World Planning via Lifted Regression with LLM-based Affordances for Embodied Agents

LLM-based Typed Hyperresolution for Commonsense Reasoning with Knowledge Bases

Reflect-then-Plan: Offline Model-Based Planning through a Doubly Bayesian Lens