Research
Find research shared by the Owlstown community.
Does learning the right latent variables necessarily improve in-context learning?
Abstract
Large autoregressive models like Transformers can solve tasks through in-context learning (ICL) without learning new weights, suggesting avenues for efficiently solving new tasks. For many tasks, e.g., linear regression, the data factor...
Publication · August 19, 2025
Sparsity regularization via tree-structured environments for disentangled representations
Abstract
Many causal systems such as biological processes in cells can only be observed indirectly via measurements, such as gene expression. Causal representation learning -- the task of correctly mapping low-level observations to latent causal...
Publication · August 19, 2025
3D Tumor-Mimicking Phantom Models for Assessing NIR I/II Nanoparticles in Fluorescence-Guided Surgical Interventions
Fluorescence image-guided surgery (FIGS) offers high spatial resolution and real-time feedback but is limited by shallow tissue penetration and autofluorescence from current clinically approved fluorophores. The near-infrared (NIR) spectrum, speci...
Publication · August 19, 2025
Standardized Electrochemical Characterization of Conductive Hydrogels
Conductive hydrogels are hydrated materials with mixed ionic‐electronic conduction that readily bridge living tissue with electronic devices. As bioelectronic interfaces are underpinned by ionic and electronic conductivity, it is important to care...
Publication · August 19, 2025
Winter dynamics of phytoplankton and micronutrients in the Southern Ocean
Publication · August 19, 2025
Latitudinal variability and adaptation of phytoplankton in the Atlantic Ocean
Publication · August 19, 2025
Sites
View all
Create your academic website in Owlstown
Start your academic website in just a few minutes. Keep it updated easily. No code, no server to maintain, so you can focus on your research.
Create your free website