activity
20232026
most citedEntropy-Informed Weighting Channel Normalizing Flow for Deep Generative Models

2 citations · 2 across the 37 of their papers we have counts for

collaborators
Showing cs.LGShow all

27 papers · 1 filter

cs.LG2026

Intervention, Not Shared Latents: Blocking Visual Shortcuts in Audio-Video Generation

Jian Xu, Delu Zeng, John Paisley

Joint audio--video (AV) generators are trained on data in which \emph{what an event looks like} and \emph{what it sounds like} are spuriously correlated. We present a \emph{control…

cs.LG2026

Partially Observed Sparse Graphs: The Unknown Sampling Rate is a Tail Index

Jian Xu, Delu Zeng, John Paisley +1

A large graph is often available only in part: a crawl stopped by its budget, a panel, a partial dump. When the sampled fraction is known by design the total edge count follows…

cs.LG2026

DiFA: Inference-Time Forward-Process Alignment for Diffusion Models

Shigui Li, Delu Zeng

The prevailing inference framework for diffusion models formulates generation fundamentally as a problem of numerical integration. This perspective casts the model as an exact esti…

cs.LG2026

When Can You Debias an LLM Judge? Identifiability Limits, a Test, and Designs for Top-k Ranking

Jian Xu, Delu Zeng, John Paisley +1

Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise. Because such judges prefer verbose or well-formatted answers,…

cs.LG2026

Active Quantum Kernel Acquisition for Gaussian Process Regression

Jian Xu, Artur Miroszewski, John Paisley +2

Quantum kernel estimation on near-term hardware is shot-budgeted: every entry of the kernel Gram matrix is a Bernoulli expectation that must be sampled with a finite number of circ…

cs.LG2026

Calibration, Not Compilation: Detecting and Repairing Misspecified Probabilistic Programs Written by Language Models

Jian Xu, Delu Zeng, John Paisley +1

Language models increasingly write probabilistic programs (in NumPyro, Stan, or Pyro), but a program that compiles, runs, and passes every unit test can still be \emph{statisticall…