7 papers
Understanding Parallel Samplers in Masked Diffusion via Random Walks on Graphs
Vansh Bansal, Cho Cholyeon, Syamantak Kumar +2
In this paper, we propose using random walks on graphs as a verifiable sandbox to study different parallel sampling strategies in masked diffusion models (MDMs). We train an MDM on…
Delta-Based Target Reformulation for Short-Term Electricity Load Forecasting Using LSTM and Transformer Models
Vansh Bansal
Accurate short-term electricity load forecasting is critical for the reliable and economic operation of modern power systems, under non-stationarity arising from weather variabilit…
On the Convergence and Straightness of Rectified Flow
Vansh Bansal, Saptarshi Roy, Alessandro Rinaldo +1
Flow Matching has become a cornerstone of modern generative models like Stable Diffusion 3, largely due to the efficiency of its Rectified Flow (RF) variant. The success of RF hing…
Conformal C2ST: Turning weak classifiers into strong two-sample tests
Vansh Bansal, Tianyu Chen, James G. Scott
The two-sample testing problem, a fundamental task in statistics and machine learning, seeks to determine whether two sets of samples, drawn from underlying distributions and $…
Score-Guided Proximal Projection: A Unified Geometric Framework for Rectified Flow Editing
Vansh Bansal, James G Scott
Rectified Flow (RF) models achieve state-of-the-art generation quality, yet controlling them for precise tasks -- such as semantic editing or blind image recovery -- remains a chal…
CoLT: The conditional localization test for assessing the accuracy of neural posterior estimates
Tianyu Chen, Vansh Bansal, James G. Scott
We consider the problem of validating whether a neural posterior estimate \( q(θ\mid x) \) is an accurate approximation to the true, unknown true posterior \( p(θ\mid x) \). Exis…