16 papers
Good Stabilizer Codes from Shallow Clifford Circuits with Random Matchings
Emile Anand, Elia Gorokhovsky, Jennifer Hritz +1
Encoding quantum information with low circuit overhead is a fundamental challenge in fault-tolerant quantum computation. Random circuits provide a natural mechanism for rapidly spr…
Role Steering of Language Models for Social Simulations
Isaac Song, Mohammed Rehan Parwani, Glenn Matlin +8
Social simulations built from language-model agents need role-conditioned behavior that can be checked before agents are placed into a simulated population. We introduce an activat…
Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures
Tyler A. Chang, Catherine Arnett, Abdelrahman Sadallah +377
To date, there exist almost no culturally-specific evaluation benchmarks for large language models (LLMs) that cover a large number of languages and cultures. In this paper, we pre…
Continuous Latent Contexts Enable Efficient Online Learning in Transformers
Emile Anand, Abdullah Ateyeh, Xinyuan Cao +1
Large language models (LLMs) exhibit a strong capacity for in-context learning: Given labeled examples, they can generate good predictions without parameter updates. However, many…
Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling
Emile Anand, Ishani Karmarkar
Many large-scale platforms and networked control systems have a centralized decision maker interacting with a massive population of agents under strict observability constraints. M…
Unsupervised Decomposition and Recombination with Discriminator-Driven Diffusion Models
Archer Wang, Emile Anand, Yilun Du +1
Decomposing complex data into factorized representations can reveal reusable components and enable synthesizing new samples via component recombination. We investigate this in the…