5 papers
FUSE: Ensembling Verifiers with Zero Labeled Data
Joonhyuk Lee, Virginia Ma, Sarah Zhao +4
Verification of model outputs is rapidly emerging as a key primitive for both training and real-world deployment of large language models (LLMs). In practice, this often involves u…
@GrokSet: multi-party Human-LLM Interactions in Social Media
Matteo Migliarini, Berat Ercevik, Oluwagbemike Olowe +5
Large Language Models (LLMs) are increasingly deployed as active participants on public social media platforms, yet their behavior in these unconstrained social environments remain…
Imputation-Powered Inference
Sarah Zhao, Emmanuel Candès
Modern multi-modal and multi-site data frequently suffer from blockwise missingness, where subsets of features are missing for groups of individuals, creating complex patterns that…
Scalable Amortized GPLVMs for Single Cell Transcriptomics Data
Sarah Zhao, Aditya Ravuri, Vidhi Lalchand +1
Dimensionality reduction is crucial for analyzing large-scale single-cell RNA-seq data. Gaussian Process Latent Variable Models (GPLVMs) offer an interpretable dimensionality reduc…
Geodesic Mode Connectivity
Charlie Tan, Theodore Long, Sarah Zhao +1
Mode connectivity is a phenomenon where trained models are connected by a path of low loss. We reframe this in the context of Information Geometry, where neural networks are studie…