3 citations · 4 across the 7 of their papers we have counts for
8 papers
EMPIRIC: Experiment-Driven Learning of Residual World Models for Robot Planning
Yichao Liang, Amber Li, Dat Nguyen +13
A robot should be able to learn through experiments how unfamiliar objects behave and interact, then plan with that knowledge. It need not start from scratch: physics engines suppl…
Benchmarking World-Model Learning with Environment-Level Queries
Archana Warrier, Dat Nguyen, Michelangelo Naim +8
World models are central to building AI agents capable of flexible reasoning and planning. Yet current evaluations (i) test only properties measurable from observed interactions, s…
ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning
Yichao Liang, Dat Nguyen, Cambridge Yang +7
Long-horizon embodied planning is challenging because the world does not only change through an agent's actions: exogenous processes (e.g., water heating, dominoes cascading) unfol…
A Neuroscience-Inspired Dual-Process Model of Compositional Generalization
Alex Noviello, Claas Beger, Jacob Groner +2
Deep learning models struggle with systematic compositional generalization, a hallmark of human cognition. We propose \textsc{Mirage}, a neuro-inspired dual-process model that offe…
Refactoring Codebases through Library Design
Ziga Kovacic, Justin T. Chiu, Celine Lee +2
Maintainable and general software allows developers to build robust applications efficiently, yet achieving these qualities often requires refactoring specialized solutions into re…
VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning
Yichao Liang, Nishanth Kumar, Hao Tang +5
Broadly intelligent agents should form task-specific abstractions that selectively expose the essential elements of a task, while abstracting away the complexity of the raw sensori…
Rapid Motor Adaptation for Robotic Manipulator Arms
Yichao Liang, Kevin Ellis, João Henriques
Developing generalizable manipulation skills is a core challenge in embodied AI. This includes generalization across diverse task configurations, encompassing variations in object…
Scaling Neural Program Synthesis with Distribution-based Search
Nathanaël Fijalkow, Guillaume Lagarde, Théo Matricon +3
We consider the problem of automatically constructing computer programs from input-output examples. We investigate how to augment probabilistic and neural program synthesis methods…