papers

Publications (24)

cs.HC2018

Automating Analysis of Construction Workers Viewing Patterns for Personalized Safety Training and Management

Idris Jeelani, Kevin Han, Alex Albert

Unrecognized hazards increase the likelihood of workplace fatalities and injuries substantially. However, recent research has demonstrated that a large proportion of hazards remain…

stat.ME2023

Model-Based Regression Adjustment with Model-Free Covariates for Network Interference

Kevin Han, Johan Ugander

When estimating a Global Average Treatment Effect (GATE) under network interference, units can have widely different relationships to the treatment depending on a combination of th…

cs.MM2024

Pegasus-v1 Technical Report

Raehyuk Jung, Hyojun Go, Jaehyuk Yi +41

This technical report introduces Pegasus-1, a multimodal language model specialized in video content understanding and interaction through natural language. Pegasus-1 is designed t…

cs.CL2026

Scaling Natural-Language Graph-Based Test Time Compute for Automated Theorem Proving

Vincent Li, Tim Knappe, Yule Fu +2

Large language models have demonstrated remarkable capabilities in natural language processing tasks requiring multi-step logical reasoning capabilities, such as automated theorem…

stat.ME2023

Detecting Interference in A/B Testing with Increasing Allocation

Kevin Han, Shuangning Li, Jialiang Mao +1

In the past decade, the technology industry has adopted online randomized controlled experiments (a.k.a. A/B testing) to guide product development and make business decisions. In p…

cs.RO2019

Real-time Scene Segmentation Using a Light Deep Neural Network Architecture for Autonomous Robot Navigation on Construction Sites

Khashayar Asadi, Pengyu Chen, Kevin Han +2

Camera-equipped unmanned vehicles (UVs) have received a lot of attention in data collection for construction monitoring applications. To develop an autonomous platform, the UV shou…

cs.AI2026

SMDD-Bench: Can LLMs Solve Real-World Small Molecule Drug Design Tasks?

Kevin Han, Renfei Zhang, Kathy Wei +3

LLM agents have incredible potential for scientific discovery applications. However, the performance of LLM agents on real-world, small molecule drug design (SMDD) tasks across div…

cond-mat.mtrl-sci2023

CHGNet: Pretrained universal neural network potential for charge-informed atomistic modeling

Bowen Deng, Peichen Zhong, KyuJung Jun +4

The simulation of large-scale systems with complex electron interactions remains one of the greatest challenges for the atomistic modeling of materials. Although classical force fi…

cs.SE2026

TDFlow: Agentic Workflows for Test Driven Development

Kevin Han, Siddharth Maddikayala, Tim Knappe +3

We introduce TDFlow, a novel test-driven agentic workflow that frames repository-scale software engineering as a test-resolution task, specifically designed to solve human-written…

cs.CY2019

Virtual Manipulation in an Immersive Virtual Environment: Simulation of Virtual Assembly

Mojtaba Noghabaei, Khashayar Asadi, Kevin Han

To fill the lack of research efforts in virtual assembly of modules and training, this paper presents a virtual manipulation of building objects in an Immersive Virtual Environment…

cs.LG2026

Smooth Dynamic Cutoffs for Machine Learning Interatomic Potentials

Kevin Han, Haolin Cong, Bowen Deng +1

Machine learning interatomic potentials (MLIPs) have proven to be wildly useful for molecular dynamics simulations, powering countless drug and materials discovery applications. Ho…

cs.CV2019

Real-world Mapping of Gaze Fixations Using Instance Segmentation for Road Construction Safety Applications

Idris Jeelani, Khashayar Asadi, Hariharan Ramshankar +2

Research studies have shown that a large proportion of hazards remain unrecognized, which expose construction workers to unanticipated safety risks. Recent studies have also found…

stat.ME2023

Estimating Treatment Effects Using Observational Data and Experimental Data with Non-overlapping Support

Kevin Han

When estimating treatment effects, the golden standard is to conduct a randomized experiment and then contrast outcomes associated with the treatment group and the control group. H…

cs.RO2019

Vision-based Obstacle Removal System for Autonomous Ground Vehicles Using a Robotic Arm

Khashayar Asadi, Rahul Jain, Ziqian Qin +5

Over the past few years, the use of camera-equipped robotic platforms for data collection and visually monitoring applications has exponentially grown. Cluttered construction sites…

physics.optics2016

Large-area, uniform and low-cost dual-mode plasmonic naked-eye colorimetry and SERS sensor with handheld Raman spectrometer

Zhida Xu, Jing Jiang, Xinhao Wang +5

We demonstrated a highly sensitive, waferscale, highly uniform plasmonic nanomushroom substrate based on plastic for nakedeye plasmonic colorimetry and surface enhanced Raman spect…

stat.ME2023

Population Interference in Panel Experiments

Kevin Han, Iavor Bojinov, Guillaume Basse

The phenomenon of population interference, where a treatment assigned to one experimental unit affects another experimental unit's outcome, has received considerable attention in s…

cs.CY2020

A Survey Study to Understand Industry Vision for Virtual and Augmented Reality Applications in Design and Construction

Mojtaba Noghabaei, Arsalan Heydarian, Vahid Balali +1

With advances in Building Information Modeling (BIM), Virtual Reality (VR) and Augmented Reality (AR) technologies have many potential applications in the Architecture, Engineering…

cs.HC2020

Hazard recognition in an immersive virtual environment: Framework for the simultaneous analysis of visual search and EEG patterns

Mojtaba Noghabaei, Kevin Han

Unmanaged hazards in dangerous construction environments proved to be one of the main sources of injuries and accidents. Hazard recognition is crucial to achieve effective safety m…

cs.AI2020

Toward Automated Virtual Assembly for Prefabricated Construction: Construction Sequencing through Simulated BIM

Gilmarie O'Neill, Matthew Ball, Yujing Liu +2

To adhere to the stringent time and budget requirements of construction projects, contractors are utilizing prefabricated construction methods to expedite the construction process.…

cs.DC2026

DistMLIP: A Distributed Inference Platform for Machine Learning Interatomic Potentials

Kevin Han, Bowen Deng, Amir Barati Farimani +1

Large-scale atomistic simulations are essential to bridge computational materials and chemistry to realistic materials and drug discovery applications. In the past few years, rapid…

cs.CV2025

Segmenting Objectiveness and Task-awareness Unknown Region for Autonomous Driving

Mi Zheng, Guanglei Yang, Zitong Huang +3

With the emergence of transformer-based architectures and large language models (LLMs), the accuracy of road scene perception has substantially advanced. Nonetheless, current road…

cs.RO2018

Building an Integrated Mobile Robotic System for Real-Time Applications in Construction

Khashayar Asadi, Hariharan Ramshankar, Harish Pullagurla +7

One of the major challenges of a real-time autonomous robotic system for construction monitoring is to simultaneously localize, map, and navigate over the lifetime of the robot, wi…

cs.LG2026

EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimization

Kevin Han, Yuhang Zhou, Mingze Gao +6

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for enhancing the reasoning capabilities of Large Language Models (LLMs). However, dominant approaches li…

cs.CL2024

Pragmatic Metacognitive Prompting Improves LLM Performance on Sarcasm Detection

Joshua Lee, Wyatt Fong, Alexander Le +3

Sarcasm detection is a significant challenge in sentiment analysis due to the nuanced and context-dependent nature of verbiage. We introduce Pragmatic Metacognitive Prompting (PMP)…