422 citations · 513 across the 40 of their papers we have counts for
41 papers
QuanVI: Score-based Variational Inference via Quantum Maximally Mixed States
Yuchen Cong, Zerui Tao, Chao Li +2
Score-based variational inference (VI) provides an alternative to Kullback--Leibler (KL)-based VI by minimizing the Fisher divergence between the variational distribution and the t…
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…
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…
Diagnosing Under-Development of Irreversible Processes in Video Generation
Jian Xu, Yanning Wu, Delu Zeng +2
Many physical attributes are \emph{irreversible}: ice melts but does not re-freeze, paper chars but does not un-burn. Do video generators respect this? We show the question is hard…
Look Again Before You Abstain:Budgeted Conformal Evidence Acquisition for Reliable Vision-Language Model
Jian Xu, Yanning Wu, Delu Zeng +2
Large vision-language models (LVLMs) hallucinate: they assert visual details that the image does not support. A principled remedy is selective prediction with a distribution-free g…
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,…
SQGen: Structured Quantum Image Generation with Latent-Modulated Quantized Tensor Trains
Guang Lin, Qibin Zhao
Generating images directly from quantum systems is an attractive but unresolved goal on NISQ hardware. Existing quantum generators face several coupled obstacles: barren plateaus t…
Fixed-Protocol Amortized MPS Tomography with Conformalized Predictive Uncertainty
Jian Xu, Delu Zeng, John Paisley +1
Quantum state tomography is sample-starved, and the states one prepares live on a narrow, learnable manifold. A prior-only control shows that on concentrated families a pri…
Entanglement as a Structural Complexity Axis: A PAC-Bayesian View of Generalization in Quantum Policies and Value Functions
Jian Xu, Delu Zeng, John Paisley +1
Parameterized quantum circuits (PQCs) are increasingly used as policies and value functions in quantum reinforcement learning, yet it remains unclear when and why quantum policies…
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…
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…
What Do Flow-Based Inverse Solvers Approximate? A Posterior-Transport View
Jian Xu, Delu Zeng, John Paisley +1
A growing family of training-free solvers -- FlowDPS, FLOWER, PnP-Flow and their diffusion ancestors (DPS, DAPS) -- repurpose a pretrained flow-matching prior to solve imaging inve…
Onsager-Machlup Posterior Transport for Deep Gaussian Processes
Jian Xu, Delu Zeng, John Paisley +1
Approximate inference over inducing variables is the central computational bottleneck of Deep Gaussian Processes (DGPs). Existing methods either fit an explicit density $q_ϕ(\bU)$…
Intrinsic Flow Matching on Quantum Pure-State Manifolds with Phase-Aligned Transport
Jian Xu, Delu Zeng, John Paisley +1
Quantum pure-state ensembles live on complex projective space, making flat Euclidean generative modeling geometrically mismatched. We introduce Intrinsic Flow Matching (IFM), a det…
Effective Dimension Governs Generalization in Quantum Kernel Vision Models
Jian Xu, Delu Zeng, John Paisley +1
Recent quantum vision models-quantum vision transformers and quantum convolutional networks-report two striking but unexplained empirical phenomena: (i) ansatze with more, or more…
Higher-Order Token Interactions via Quantum Attention
Jian Xu, Chao Li, Delu Zeng +2
Standard dot-product self-attention computes, in a single layer, only pairwise (order-2) interactions between tokens; representing a generic order- interaction is known to requi…
Bayesian Tensor Decomposition with Diffusion Model Prior
Zerui Tao, Qibin Zhao
Low-rank tensor decomposition (TD) is usually effective on clean, fully observed data, but it often degrades under severe missingness or noise. Low-rankness is itself a useful but…
Implicit Variational Rejection Sampling
Jian Xu, Shigui Li, Wei Chen +6
Variational Inference (VI) is a fundamental inference technique in Bayesian machine learning for approximating complex posterior distributions. Traditional VI often relies on the m…
Deep Unfolded Latent Optimally Partitioned-l2/l1 Networks for Data-driven Block-Sparse Recovery
Takanobu Furuhashi, Hidekata Hontani, Qibin Zhao +1
The convex Latent Optimal Partition (LOP)-l2/l1 approach enables block-sparse signal recovery with unknown partitions but relies on manual hyperparameter tuning. Additionally, nume…
The Right Measure for Physics-Constrained Generation: A Co-Area Correction for Posterior-Consistent PDE Inverse Problems
Jian Xu, Yanning Wu, Delu Zeng +2
Generative models -- diffusion and flow matching -- are increasingly used to solve partial differential equation (PDE) inverse problems, enforcing the governing physics as a \emph{…
Tensorizing Engram: Sharing Latents Across N-Gram Embeddings is Beneficial in LLMs
Wuyang Zhou, Yuxuan Gu, Giorgos Iacovides +3
Modern language models represent text using discrete token-level embeddings, which forces recurring multi-token patterns to be learned implicitly across Transformer layers. Both Ov…
Spectral Anatomy of Quantum Gaussian Process Kernels
Jian Xu, Chao Li, Guang Lin +4
Two recent results have reshaped quantum Gaussian processes (QGPs). On the one hand, \citet{lowe2025assessing} rule out the exponential speedups claimed by HHL-based QGP regression…
On the Approximation Complexity of Matrix Product Operator (MPO) Born Machines
Chao Li, Zerui Tao, Yuchen Cong +2
Matrix product operator Born machines (MPO-BMs) are tractable tensor-network models for probabilistic modeling, yet their approximation capabilities remain poorly understood in the…
AQKA: Active Quantum Kernel Acquisition Under a Shot Budget
Jian Xu, Chao Li, Delu Zeng +2
Estimating an quantum kernel from circuit fidelities requires measurement shots, the dominant bottleneck for deployment on near-term hardware. Existing budg…