565 citations · 2.3k across the 35 of their papers we have counts for
38 papers
A game theory for foundation models shows new paths to rational cooperation through similarity inference
Alexander Meulemans, Maciej Wołczyk, Marissa A. Weis +11
As autonomous agents powered by foundation models are increasingly integrated into social and economic systems, understanding the principles governing their collective behavior is…
Coevolution of self-replication and function in a digital primordial soup
Francesco Cicala, Eyvind Niklasson, Ettore Randazzo +8
While traditional evolutionary algorithms hard-code reproduction, self-replication can emerge spontaneously within digital ``primordial soups''. This paper investigates the coevolu…
BFF: Simple explanations for complex phenomena
Charlotte Knierim, Luca Versari, Robert Obryk +2
The ''Computational Life'' paper (Agüera y Arcas et al., 2024) argues that paired interactions in a computational soup are an effective way to find self-replicators. In this work,…
Can In-Context Learning Support Intrinsic Curiosity?
Eric Elmoznino, Sangnie Bhardwaj, Johannes von Oswald +5
Effective machine learning depends not only on how we model data, but also on what data we choose to collect. While large sequence models have revolutionized data modeling, the pro…
Multi-agent cooperation through in-context co-player inference
Marissa A. Weis, Maciej Wołczyk, Rajai Nasser +4
Achieving cooperation among self-interested agents remains a fundamental challenge in multi-agent reinforcement learning. Recent work showed that mutual cooperation can be induced…
Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning
Seijin Kobayashi, Yanick Schimpf, Maximilian Schlegel +12
Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecedented success on many problem domains. Du…
Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning
Alexander Meulemans, Rajai Nasser, Maciej Wołczyk +10
The standard theory of model-free reinforcement learning assumes that the environment dynamics are stationary and that agents are decoupled from their environment, such that polici…
When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors
Scott Emmons, Erik Jenner, David K. Elson +5
While chain-of-thought (CoT) monitoring is an appealing AI safety defense, recent work on "unfaithfulness" has cast doubt on its reliability. These findings highlight an important…
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
Johannes von Oswald, Nino Scherrer, Seijin Kobayashi +14
Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention. Although widely adopted, transformers require scaling memory and compu…
All Random Features Representations are Equivalent
Luke Sernau, Silvano Bonacina, Rif A. Saurous
Random features are a powerful technique for rewriting positive-definite kernels as linear products. They bring linear tools to bear in important nonlinear domains like KNNs and at…
Robust Inverse Graphics via Probabilistic Inference
Tuan Anh Le, Pavel Sountsov, Matthew D. Hoffman +3
How do we infer a 3D scene from a single image in the presence of corruptions like rain, snow or fog? Straightforward domain randomization relies on knowing the family of corruptio…
Training Chain-of-Thought via Latent-Variable Inference
Du Phan, Matthew D. Hoffman, David Dohan +7
Large language models (LLMs) solve problems more accurately and interpretably when instructed to work out the answer step by step using a ``chain-of-thought'' (CoT) prompt. One can…
Sequential Monte Carlo Learning for Time Series Structure Discovery
Feras A. Saad, Brian J. Patton, Matthew D. Hoffman +2
This paper presents a new approach to automatically discovering accurate models of complex time series data. Working within a Bayesian nonparametric prior over a symbolic space of…
Grammar Prompting for Domain-Specific Language Generation with Large Language Models
Bailin Wang, Zi Wang, Xuezhi Wang +3
Large language models (LLMs) can learn to perform a wide range of natural language tasks from just a handful of in-context examples. However, for generating strings from highly str…
ProbNeRF: Uncertainty-Aware Inference of 3D Shapes from 2D Images
Matthew D. Hoffman, Tuan Anh Le, Pavel Sountsov +4
The problem of inferring object shape from a single 2D image is underconstrained. Prior knowledge about what objects are plausible can help, but even given such prior knowledge the…
Language Model Cascades
David Dohan, Winnie Xu, Aitor Lewkowycz +9
Prompted models have demonstrated impressive few-shot learning abilities. Repeated interactions at test-time with a single model, or the composition of multiple models together, fu…
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…
tfp.mcmc: Modern Markov Chain Monte Carlo Tools Built for Modern Hardware
Junpeng Lao, Christopher Suter, Ian Langmore +7
Markov chain Monte Carlo (MCMC) is widely regarded as one of the most important algorithms of the 20th century. Its guarantees of asymptotic convergence, stability, and estimator-v…
Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision
Aren Jansen, Daniel P. W. Ellis, Shawn Hershey +4
Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-lab…
Automatically Batching Control-Intensive Programs for Modern Accelerators
Alexey Radul, Brian Patton, Dougal Maclaurin +2
We present a general approach to batching arbitrary computations for accelerators such as GPUs. We show orders-of-magnitude speedups using our method on the No U-Turn Sampler (NUTS…
Simple, Distributed, and Accelerated Probabilistic Programming
Dustin Tran, Matthew Hoffman, Dave Moore +5
We describe a simple, low-level approach for embedding probabilistic programming in a deep learning ecosystem. In particular, we distill probabilistic programming down to a single…
Differentiable Consistency Constraints for Improved Deep Speech Enhancement
Scott Wisdom, John R. Hershey, Kevin Wilson +4
In recent years, deep networks have led to dramatic improvements in speech enhancement by framing it as a data-driven pattern recognition problem. In many modern enhancement system…
Exploring Tradeoffs in Models for Low-latency Speech Enhancement
Kevin Wilson, Michael Chinen, Jeremy Thorpe +5
We explore a variety of neural networks configurations for one- and two-channel spectrogram-mask-based speech enhancement. Our best model improves on previous state-of-the-art perf…
VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking
Quan Wang, Hannah Muckenhirn, Kevin Wilson +7
In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We ac…