4 citations · 5 across the 17 of their papers we have counts for
19 papers
Thinking with Anchors: Grounded and Efficient Document Reasoning
Sichen Zhu, Yuchen Zhu, Wenzhuo Xu +13
Existing document understanding benchmarks have largely focused on locating page elements, yet real-world document intelligence requires models to reason jointly about region seman…
Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations
Zichao Li, Gang Wu, Zichao Wang +5
Large language model agents operate in partially observable, long-horizon settings where obtaining supervision remains a major bottleneck. We address this by utilizing a source of…
FLARE: Diffusion for Hybrid Language Model
Yuchen Zhu, Jing Shi, Chongjian Ge +9
Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-latency deployment. Recent efficien…
Conformalized Percentile Interval: Finite Sample Validity and Improved Conditional Performance
Ran Zou, Wanrong Zhu, Bin Nan
Conformal prediction provides distribution-free predictive intervals with finite-sample marginal coverage. However, achieving conditional validity and interval efficiency (in terms…
Refining Covariance Matrix Estimation in Stochastic Gradient Descent Through Bias Reduction
Ziyang Wei, Wanrong Zhu, Jingyang Lyu +1
We study online inference and asymptotic covariance estimation for the stochastic gradient descent (SGD) algorithm. While classical methods (such as plug-in and batch-means estimat…
AnyDoc: Enhancing Document Generation via Large-Scale HTML/CSS Data Synthesis and Height-Aware Reinforcement Optimization
Jiawei Lin, Wanrong Zhu, Vlad I Morariu +1
Document generation has gained growing attention in the field of AI-driven content creation. In this work, we push its boundaries by introducing AnyDoc, a framework capable of hand…
MiLDEdit: Reasoning-Based Multi-Layer Design Document Editing
Zihao Lin, Wanrong Zhu, Jiuxiang Gu +8
Real-world design documents (e.g., posters) are inherently multi-layered, combining decoration, text, and images. Editing them from natural-language instructions requires fine-grai…
A Flexible Empirical Bayes Approach to Generalized Linear Models, with Applications to Sparse Logistic Regression
Dongyue Xie, Matthew Stephens
We introduce a flexible empirical Bayes approach for fitting Bayesian generalized linear models. Specifically, we adopt a novel mean-field variational inference (VI) method and the…
Text-Conditioned Background Generation for Editable Multi-Layer Documents
Taewon Kang, Joseph K J, Chris Tensmeyer +4
We present a framework for document-centric background generation with multi-page editing and thematic continuity. To ensure text regions remain readable, we employ a latent maskin…
OIDA-QA: A Multimodal Benchmark for Analyzing the Opioid Industry Documents Archive
Xuan Shen, Brian Wingenroth, Zichao Wang +12
The opioid crisis represents a significant moment in public health that reveals systemic shortcomings across regulatory systems, healthcare practices, corporate governance, and pub…
GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding
Shijie Zhou, Viet Dac Lai, Hao Tan +4
Graphical user interface (GUI) grounding is a key capability for computer-use agents, mapping natural-language instructions to actionable regions on the screen. Existing Multimodal…
Online Statistical Inference of Constrained Stochastic Optimization via Random Scaling
Xinchen Du, Wanrong Zhu, Wei Biao Wu +1
Constrained stochastic nonlinear optimization problems have attracted significant attention for their ability to model complex real-world scenarios in physics, economics, and biolo…
Towards Visual Text Grounding of Multimodal Large Language Model
Ming Li, Ruiyi Zhang, Jian Chen +7
Despite the existing evolution of Multimodal Large Language Models (MLLMs), a non-neglectable limitation remains in their struggle with visual text grounding, especially in text-ri…
Conformal prediction after data-dependent model selection
Ruiting Liang, Wanrong Zhu, Rina Foygel Barber
Given a family of pretrained models and a hold-out set, how can we construct a valid conformal prediction set while selecting a model that minimizes the width of the set? If we use…
GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling
Hritik Bansal, Po-Nien Kung, P. Jeffrey Brantingham +2
Multimodal event argument role labeling (EARL), a task that assigns a role for each event participant (object) in an image is a complex challenge. It requires reasoning over the en…
High Confidence Level Inference is Almost Free using Parallel Stochastic Optimization
Wanrong Zhu, Zhipeng Lou, Ziyang Wei +1
Uncertainty quantification for estimation through stochastic optimization solutions in an online setting has gained popularity recently. This paper introduces a novel inference met…
Approximate co-sufficient sampling with regularization
Wanrong Zhu, Rina Foygel Barber
In this work, we consider the problem of goodness-of-fit (GoF) testing for parametric models. This testing problem involves a composite null hypothesis, due to the unknown values o…
Weighted Averaged Stochastic Gradient Descent: Asymptotic Normality and Optimality
Ziyang Wei, Wanrong Zhu, Wei Biao Wu
Stochastic Gradient Descent (SGD) is one of the most popular algorithms in statistical and machine learning due to its computational and memory efficiency. Various averaging scheme…
Online Covariance Matrix Estimation in Stochastic Gradient Descent
Wanrong Zhu, Xi Chen, Wei Biao Wu
The stochastic gradient descent (SGD) algorithm is widely used for parameter estimation, especially for huge data sets and online learning. While this recursive algorithm is popula…