27 citations · 64 across the 25 of their papers we have counts for
28 papers
Vision-Language Model Confidence Is Not a Property of the Answer
Reza Khanmohammadi, Erfan Miahi, Ivan Brugere +4
Vision-language models are increasingly deployed behind a confidence gate: the system reads how confident the model is in its answer and defers when confidence is low. This makes t…
Confidence Estimation for Financial Vision-Language Models in Chart and Document Understanding
Reza Khanmohammadi, Simerjot Kaur, Charese H. Smiley +2
LVLMs are increasingly used to read financial charts, tables, and documents, where a single misread figure can move a decision and the most authoritative-looking answer is sometime…
Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms
Yvonne Zhou, Mingyu Liang, Ivan Brugere +5
We present the first theoretical convergence analysis of machine learning training under fully homomorphic encryption (FHE), combined with a differentially private (DP) training al…
Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking
Reza Khanmohammadi, Erfan Miahi, Simerjot Kaur +4
Large vision-language models (LVLMs) suffer from visual ungroundedness: they can produce a fluent, confident, and even correct response driven entirely by language priors, with the…
The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
Hsiang Hsu, Pradeep Niroula, Zichang He +3
Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data. While existing methods certify unle…
How Reliable are Confidence Estimators for Large Reasoning Models? A Systematic Benchmark on High-Stakes Domains
Reza Khanmohammadi, Erfan Miahi, Simerjot Kaur +4
The miscalibration of Large Reasoning Models (LRMs) undermines their reliability in high-stakes domains, necessitating methods to accurately estimate the confidence of their long-f…
Calibrating LLM Confidence by Probing Perturbed Representation Stability
Reza Khanmohammadi, Erfan Miahi, Mehrsa Mardikoraem +5
Miscalibration in Large Language Models (LLMs) undermines their reliability, highlighting the need for accurate confidence estimation. We introduce CCPS (Calibrating LLM Confidence…
MAFE: Enabling Equitable Algorithm Design in Multi-Agent Multi-Stage Decision-Making Systems
Zachary McBride Lazri, Anirudh Nakra, Ivan Brugere +5
Algorithmic fairness is often studied in static or single-agent settings, yet many real-world decision-making systems involve multiple interacting entities whose multi-stage action…
Interpretable LLM-based Table Question Answering
Giang Nguyen, Ivan Brugere, Shubham Sharma +3
Interpretability in Table Question Answering (Table QA) is critical, especially in high-stakes domains like finance and healthcare. While recent Table QA approaches based on Large…
Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models
Wenzhuo Tang, Haitao Mao, Danial Dervovic +4
Models for natural language and images benefit from data scaling behavior: the more data fed into the model, the better they perform. This 'better with more' phenomenon enables the…
BuDDIE: A Business Document Dataset for Multi-task Information Extraction
Ran Zmigrod, Dongsheng Wang, Mathieu Sibue +10
The field of visually rich document understanding (VRDU) aims to solve a multitude of well-researched NLP tasks in a multi-modal domain. Several datasets exist for research on spec…
Balancing Fairness and Accuracy in Data-Restricted Binary Classification
Zachary McBride Lazri, Danial Dervovic, Antigoni Polychroniadou +3
Applications that deal with sensitive information may have restrictions placed on the data available to a machine learning (ML) classifier. For example, in some applications, a cla…
Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
Yvonne Zhou, Mingyu Liang, Ivan Brugere +4
The growing use of machine learning (ML) has raised concerns that an ML model may reveal private information about an individual who has contributed to the training dataset. To pre…
The Influence of Biomedical Research on Future Business Funding: Analyzing Scientific Impact and Content in Industrial Investments
Reza Khanmohammadi, Simerjot Kaur, Charese H. Smiley +4
This paper investigates the relationship between scientific innovation in biomedical sciences and its impact on industrial activities, focusing on how the historical impact and con…
A Canonical Data Transformation for Achieving Inter- and Within-group Fairness
Zachary McBride Lazri, Ivan Brugere, Xin Tian +4
Increases in the deployment of machine learning algorithms for applications that deal with sensitive data have brought attention to the issue of fairness in machine learning. Many…
Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access
Akshaj Kumar Veldanda, Ivan Brugere, Sanghamitra Dutta +2
Fair machine learning methods seek to train models that balance model performance across demographic subgroups defined over sensitive attributes like race and gender. Although sens…
Comparing Apples to Oranges: Learning Similarity Functions for Data Produced by Different Distributions
Leonidas Tsepenekas, Ivan Brugere, Freddy Lecue +1
Similarity functions measure how comparable pairs of elements are, and play a key role in a wide variety of applications, e.g., notions of Individual Fairness abiding by the semina…
Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale
Akshaj Kumar Veldanda, Ivan Brugere, Jiahao Chen +3
The success of DNNs is driven by the counter-intuitive ability of over-parameterized networks to generalize, even when they perfectly fit the training data. In practice, test error…
Parameterized Explanations for Investor / Company Matching
Simerjot Kaur, Ivan Brugere, Andrea Stefanucci +3
Matching companies and investors is usually considered a highly specialized decision making process. Building an AI agent that can automate such recommendation process can signific…
GAEA: Graph Augmentation for Equitable Access via Reinforcement Learning
Govardana Sachithanandam Ramachandran, Ivan Brugere, Lav R. Varshney +1
Disparate access to resources by different subpopulations is a prevalent issue in societal and sociotechnical networks. For example, urban infrastructure networks may enable certai…
Privacy Shadow: Measuring Node Predictability and Privacy Over Time
Ivan Brugere, Tanya y. Berger-Wolf
The structure of network data enables simple predictive models to leverage local correlations between nodes to high accuracy on tasks such as attribute and link prediction. While t…
Inferring Network Structure From Data
Ivan Brugere, Tanya Y. Berger-Wolf
Networks are complex models for underlying data in many application domains. In most instances, raw data is not natively in the form of a network, but derived from sensors, logs, i…
Network Model Selection Using Task-Focused Minimum Description Length
Ivan Brugere, Tanya Y. Berger-Wolf
Networks are fundamental models for data used in practically every application domain. In most instances, several implicit or explicit choices about the network definition impact t…
Network Model Selection for Task-Focused Attributed Network Inference
Ivan Brugere, Chris Kanich, Tanya Y. Berger-Wolf
Networks are models representing relationships between entities. Often these relationships are explicitly given, or we must learn a representation which generalizes and predicts ob…