🏢 Brown University

R3GAN, a minimalist GAN baseline, surpasses state-of-the-art models by using a novel regularized relativistic GAN loss and modern architectures, proving GANs can be trained efficiently without relying…

Text-Aware Diffusion for Policy Learning (TADPoLe) uses pretrained diffusion models for zero-shot reward generation, enabling natural language-driven policy learning without manual reward design.

Transformer Language Models’ (LMs) sensitivity to seemingly arbitrary prompt changes is explained by identifying low-rank communication channels between layers. By decomposing attention heads, resear…

RTify: A novel framework aligns deep neural networks’ dynamics with human reaction times for improved visual decision-making models.

AI learns to edit visual programs more accurately using a self-supervised method that combines one-shot program generation with iterative local edits, significantly boosting performance, especially wi…

This paper introduces a novel formalization of feint behaviors in multi-player games, improving AI performance and game diversity via a unified MARL implementation.

Vision transformers surprisingly struggle with visual relations; this study reveals ViTs use distinct perceptual and relational processing stages to solve same/different tasks, highlighting a previous…