7 papers
FedQHD: Closed-Form Function-Space Federated Reinforcement Learning
Yuchen Hou, Yongshan Chen, Zhuowen Zou +4
Federated reinforcement learning enables decentralized agents to collaboratively improve policies or value estimates without exchanging raw trajectories. However, FedAvg-style para…
ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions
Prathyush Poduval, Calvin Yeung, Neel Desai +1
Sparse autoencoders are usually trained one layer at a time, even though transformer residual stream activations are strongly coupled across depth. This creates a practical problem…
Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models
Calvin Yeung, Prathyush Poduval, Ali Zakeri +2
Text-to-image diffusion models generate images through an iterative denoising process, so internal neural layers produce trajectories of activations rather than single static repre…
Generalized Holographic Reduced Representations
Calvin Yeung, Zhuowen Zou, SungHeon Jeong +3
Hyperdimensional Computing (HDC) is a computationally and data-efficient paradigm that acts as a bridge between connectionist and symbolic approaches to artificial intelligence (AI…
Geometric Priors for Generalizable World Models via Vector Symbolic Architecture
William Youngwoo Chung, Calvin Yeung, Hansen Jin Lillemark +3
A key challenge in artificial intelligence and neuroscience is understanding how neural systems learn representations that capture the underlying dynamics of the world. Most world…
Coupled Inference in Diffusion Models for Semantic Decomposition
Calvin Yeung, Ali Zakeri, Zhuowen Zou +1
Many visual scenes can be described as compositions of latent factors. Effective recognition, reasoning, and editing often require not only forming such compositional representatio…