SSA and DA extract barrier-sensitive mode separation from the autocovariance matrix of a unique constant-coefficient diffusion with the given density as stationary distribution.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 2representative citing papers
In a controlled synthetic setting, transformers implement in-distribution task inference via convex combinations of task vectors and out-of-distribution inference via nearly orthogonal extrapolative representations.
This work establishes identification conditions and marginal g-formulas for causal effects under dynamic treatment regimes in marked point process data by adapting discrete-time causal assumptions via martingale theory.
A plug-in estimator for tilted distributions is minimax-optimal, with Wasserstein closeness bounds to the true tilted distribution and TV-accuracy guarantees when running diffusion on the estimated samples.
citing papers explorer
-
Measuring and Decomposing Mode Separation via the Canonical Diffusion
SSA and DA extract barrier-sensitive mode separation from the autocovariance matrix of a unique constant-coefficient diffusion with the given density as stationary distribution.
-
Task Vector Geometry Underlies Dual Modes of Task Inference in Transformers
In a controlled synthetic setting, transformers implement in-distribution task inference via convex combinations of task vectors and out-of-distribution inference via nearly orthogonal extrapolative representations.
-
On causal inference with marked point process data
This work establishes identification conditions and marginal g-formulas for causal effects under dynamic treatment regimes in marked point process data by adapting discrete-time causal assumptions via martingale theory.
-
Generating DDPM-based Samples from Tilted Distributions
A plug-in estimator for tilted distributions is minimax-optimal, with Wasserstein closeness bounds to the true tilted distribution and TV-accuracy guarantees when running diffusion on the estimated samples.