Follow the ideas that keep turning up in Hacker News discussions.
Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai +3
Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools.
Kevin Meng, David Bau, Alex Andonian +1
We analyze the storage and recall of factual associations in autoregressive transformer language models, finding evidence that these associations correspond to localized, directly-editable computations.
Cynthia Solomon, Brian Harvey, Ken Kahn +5
Logo is more than a programming language.
Joel Lehman, Jonathan Gordon, Shawn Jain +3
This paper pursues the insight that large language models (LLMs) trained to generate code can vastly improve the effectiveness of mutation operators applied to programs in genetic programming (GP).
Sergey Levine, Chelsea Finn, Trevor Darrell +1
Policy search methods can allow robots to learn control policies for a wide range of tasks, but practical applications of policy search often require hand-engineered components for perception, state estimation, and low-level control.
Chen Qian, Wei Liu, Hongzhang Liu +11
Software development is a complex task that necessitates cooperation among multiple members with diverse skills.
Guanzhi Wang, Yuqi Xie, Yunfan Jiang +5
We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention.
Axel Backlund, Lukas Petersson
While Large Language Models (LLMs) can exhibit impressive proficiency in isolated, short-term tasks, they often fail to maintain coherent performance over longer time horizons.
Paul Christiano, Jan Leike, Tom B. Brown +3
For sophisticated reinforcement learning (RL) systems to interact usefully with real-world environments, we need to communicate complex goals to these systems.
Melanie Mitchell
Since its beginning in the 1950s, the field of artificial intelligence has cycled several times between periods of optimistic predictions and massive investment ("AI spring") and periods of disappointment, loss of confidence, and reduced funding ("AI winter").
Alexander Novikov, Ngân Vũ, Marvin Eisenberger +15
In this white paper, we present AlphaEvolve, an evolutionary coding agent that substantially enhances capabilities of state-of-the-art LLMs on highly challenging tasks such as tackling open scientific problems or optimizing critical pieces of computational infrastructure.
Timothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel +5
We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain.
Laurent Dinh, Jascha Sohl-Dickstein, Samy Bengio
Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning.
Max Willsey, Chandrakana Nandi, Yisu Remy Wang +3
An e-graph efficiently represents a congruence relation over many expressions.
Carlos E. Jimenez, John Yang, Alexander Wettig +4
Language models have outpaced our ability to evaluate them effectively, but for their future development it is essential to study the frontier of their capabilities.
Zeyuan Allen-Zhu, Yuanzhi Li
Scaling laws describe the relationship between the size of language models and their capabilities.
Josh Tobin, Rachel Fong, Alex Ray +3
Bridging the 'reality gap' that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability.
Jiajun Lu, Hussein Sibai, Evan Fabry +1
It has been shown that most machine learning algorithms are susceptible to adversarial perturbations.
Horia Mania, Aurelia Guy, Benjamin Recht
A common belief in model-free reinforcement learning is that methods based on random search in the parameter space of policies exhibit significantly worse sample complexity than those that explore the space of actions.
Erik W. Lentz
Solitons in space-time capable of transporting time-like observers at superluminal speeds have long been tied to violations of the weak, strong, and dominant energy conditions of general relativity.
Xingyao Wang, Yangyi Chen, Lifan Yuan +4
Large Language Model (LLM) agents, capable of performing a broad range of actions, such as invoking tools and controlling robots, show great potential in tackling real-world challenges.
James W. A. Strachan, Dalila Albergo, Giulia Borghini +9
Abstract At the core of what defines us as humans is the concept of theory of mind: the ability to track other people’s mental states.
Marc G. Bellemare, Salvatore Candido, Pablo Samuel Castro +5
Jonas Degrave, Federico Felici, Jonas Buchli +28
Abstract Nuclear fusion using magnetic confinement, in particular in the tokamak configuration, is a promising path towards sustainable energy.
Anja Mizdrak, Linda J Cobiac, Christine L Cleghorn +2
AbstractReducing motorized transport and increasing active transport (i.e.