6 citations · 14 across the 12 of their papers we have counts for
12 papers
AutoHarness: improving LLM agents by automatically synthesizing a code harness
Xinghua Lou, Miguel Lázaro-Gredilla, Antoine Dedieu +3
Despite significant strides in language models in the last few years, when used as agents, such models often try to perform actions that are not just suboptimal for a given state,…
Joint Learning of Hierarchical Neural Options and Abstract World Model
Wasu Top Piriyakulkij, Wolfgang Lehrach, Kevin Ellis +1
Building agents that can perform new skills by composing existing skills is a long-standing goal of AI agent research. Towards this end, we investigate how to efficiently acquire a…
Code World Models for General Game Playing
Wolfgang Lehrach, Daniel Hennes, Miguel Lazaro-Gredilla +13
Large Language Models (LLMs) reasoning abilities are increasingly being applied to classical board and card games, but the dominant approach -- involving prompting for direct move…
Improving Transformer World Models for Data-Efficient RL
Antoine Dedieu, Joseph Ortiz, Xinghua Lou +5
We present three improvements to the standard model-based RL paradigm based on transformers: (a) "Dyna with warmup", which trains the policy on real and imaginary data, but only st…
Diffusion Model Predictive Control
Guangyao Zhou, Sivaramakrishnan Swaminathan, Rajkumar Vasudeva Raju +6
We propose Diffusion Model Predictive Control (D-MPC), a novel MPC approach that learns a multi-step action proposal and a multi-step dynamics model, both using diffusion models, a…
DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors
Joseph Ortiz, Antoine Dedieu, Wolfgang Lehrach +7
Learning from previously collected data via behavioral cloning or offline reinforcement learning (RL) is a powerful recipe for scaling generalist agents by avoiding the need for ex…
Learning Cognitive Maps from Transformer Representations for Efficient Planning in Partially Observed Environments
Antoine Dedieu, Wolfgang Lehrach, Guangyao Zhou +2
Despite their stellar performance on a wide range of tasks, including in-context tasks only revealed during inference, vanilla transformers and variants trained for next-token pred…
Graphical Models with Attention for Context-Specific Independence and an Application to Perceptual Grouping
Guangyao Zhou, Wolfgang Lehrach, Antoine Dedieu +2
Discrete undirected graphical models, also known as Markov Random Fields (MRFs), can flexibly encode probabilistic interactions of multiple variables, and have enjoyed successful a…
Query Training: Learning a Worse Model to Infer Better Marginals in Undirected Graphical Models with Hidden Variables
Miguel Lázaro-Gredilla, Wolfgang Lehrach, Nishad Gothoskar +3
Probabilistic graphical models (PGMs) provide a compact representation of knowledge that can be queried in a flexible way: after learning the parameters of a graphical model once,…
Learning undirected models via query training
Miguel Lazaro-Gredilla, Wolfgang Lehrach, Dileep George
Typical amortized inference in variational autoencoders is specialized for a single probabilistic query. Here we propose an inference network architecture that generalizes to unsee…
Learning higher-order sequential structure with cloned HMMs
Antoine Dedieu, Nishad Gothoskar, Scott Swingle +3
Variable order sequence modeling is an important problem in artificial and natural intelligence. While overcomplete Hidden Markov Models (HMMs), in theory, have the capacity to rep…
Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data
Xinghua Lou, Ken Kansky, Wolfgang Lehrach +4
We demonstrate that a generative model for object shapes can achieve state of the art results on challenging scene text recognition tasks, and with orders of magnitude fewer traini…