LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
A statistical inference framework for day-to-day traffic dynamics models allows identifiability, consistency proofs, and parameter estimation from trajectory data, with extensions for heterogeneity and privacy, validated on simulations and Ann Arbor data.
A recursive cubing framework identifies stable hyperparameter regions for MC dropout uncertainty quantification in spatial deep learning and produces competitive or superior predictive intervals versus a statistical baseline on simulations and land-surface temperature data.
citing papers explorer
-
Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.
-
Statistical Inference of Day-to-Day Traffic Dynamics
A statistical inference framework for day-to-day traffic dynamics models allows identifiability, consistency proofs, and parameter estimation from trajectory data, with extensions for heterogeneity and privacy, validated on simulations and Ann Arbor data.
-
A Cubing Strategy for Identifying Stable Hyperparameter Regions for Uncertainty Quantification in Spatial Deep Learning
A recursive cubing framework identifies stable hyperparameter regions for MC dropout uncertainty quantification in spatial deep learning and produces competitive or superior predictive intervals versus a statistical baseline on simulations and land-surface temperature data.
- Adaptive Generalized Elliptical Slice Sampling