Publications (26)
Benchmarking ERP Analysis: Manual Features, Deep Learning, and Foundation Models
Yihe Wang, Zhiqiao Kang, Bohan Chen +2
Event-related potential (ERP), a specialized paradigm of electroencephalographic (EEG), reflects neurological responses to external stimuli or events, generally associated with the…
Variational Flow Maps: Make Some Noise for One-Step Conditional Generation
Abbas Mammadov, So Takao, Bohan Chen +4
Flow maps enable high-quality image generation in a single forward pass. However, unlike iterative diffusion models, their lack of an explicit sampling trajectory impedes incorpora…
Learning to Coordinate Symbolic Tools: LLM Agents for Verified Sum-of-Squares Certificates
Bohan Chen, Shivam N. Patel, Richard Hoffmann +2
Tool calling allows large language models (LLMs) to invoke external computation during problem solving, a useful capability in various fields including AI for mathematics. We study…
Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering
Zeyu Liu, Weicong Liang, Yiming Zhao +5
Recently, Glyph-ByT5 has achieved highly accurate visual text rendering performance in graphic design images. However, it still focuses solely on English and performs relatively po…
Learning Probabilistic Filters with Strictly Proper Scoring Rules
Eviatar Bach, Ricardo Baptista, Jochen Bröcker +2
Bayesian filtering of partially and noisily observed dynamical systems seeks to infer the evolving conditional distribution of the state of a dynamical system, given observations,…
Importance sampling of heavy-tailed iterated random functions
Bohan Chen, Chang-Han Rhee, Bert Zwart
We consider a stochastic recurrence equation of the form , where , and $\{(A_n,B_n)\}_{n\in\m…
GLL: A Differentiable Graph Learning Layer for Neural Networks
Jason Brown, Bohan Chen, Harris Hardiman-Mostow +2
Standard deep learning architectures used for classification generate label predictions with a projection head and softmax activation function. Although successful, these methods f…
AutoKG: Efficient Automated Knowledge Graph Generation for Language Models
Bohan Chen, Andrea L. Bertozzi
Traditional methods of linking large language models (LLMs) to knowledge bases via the semantic similarity search often fall short of capturing complex relational dynamics. To addr…
OpsEval: A Comprehensive IT Operations Benchmark Suite for Large Language Models
Yuhe Liu, Changhua Pei, Longlong Xu +13
Information Technology (IT) Operations (Ops), particularly Artificial Intelligence for IT Operations (AIOps), is the guarantee for maintaining the orderly and stable operation of e…
Revisiting DETR Pre-training for Object Detection
Yan Ma, Weicong Liang, Bohan Chen +5
Motivated by the remarkable achievements of DETR-based approaches on COCO object detection and segmentation benchmarks, recent endeavors have been directed towards elevating their…
Simulation of stochastic Volterra equations driven by space--time Lévy noise
Bohan Chen, Carsten Chong, Claudia Klüppelberg
In this paper we investigate two numerical schemes for the simulation of stochastic Volterra equations driven by space--time Lévy noise of pure-jump type. The first one is based o…
Graph-based Active Learning for Surface Water and Sediment Detection in Multispectral Images
Bohan Chen, Kevin Miller, Andrea L. Bertozzi +1
We develop a graph active learning pipeline (GAP) to detect surface water and in-river sediment pixels in satellite images. The active learning approach is applied within the train…
MRATTS: An MR-Based Acupoint Therapy Training System with Real-Time Acupoint Detection and Evaluation Standards
Jiacheng Liu, Bohan Chen, Qian Wang +5
Acupoint therapy is a core therapeutic method of Traditional Chinese Medicine (TCM), and it requires a high level of expertise and skills to detect acupoints and perform acupunctur…
Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization
Zhanhao Liang, Yuhui Yuan, Shuyang Gu +5
Generating visually appealing images is fundamental to modern text-to-image generation models. A potential solution to better aesthetics is direct preference optimization (DPO), wh…
Novel Batch Active Learning Approach and Its Application to Synthetic Aperture Radar Datasets
James Chapman, Bohan Chen, Zheng Tan +3
Active learning improves the performance of machine learning methods by judiciously selecting a limited number of unlabeled data points to query for labels, with the aim of maximal…
Sample-path large deviations for a class of heavy-tailed Markov additive processes
Bohan Chen, Chang-Han Rhee, Bert Zwart
For a class of additive processes driven by the affine recursion , we develop a sample-path large deviations principle in the topology on .…
Inkjet Printed Liquid Crystal Droplet for Complex Beam Manipulation
Mengmeng Li, Chao He, Steve J. Elston +6
The inkjet-fabricated liquid crystal (LC) droplet device not only capitalizes on the intrinsic birefringence properties of liquid crystals but also leverages the hemispherical shap…
Efficient Rare-Event Simulation for Multiple Jump Events in Regularly Varying Random Walks and Compound Poisson Processes
Bohan Chen, Jose Blanchet, Chang-Han Rhee +1
We propose a class of strongly efficient rare event simulation estimators for random walks and compound Poisson processes with a regularly varying increment/jump-size distribution…
Learning Enhanced Ensemble Filters
Eviatar Bach, Ricardo Baptista, Edoardo Calvello +2
The filtering distribution in hidden Markov models evolves according to the law of a mean-field model in state-observation space. The ensemble Kalman filter (EnKF) approximates thi…
BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation
Yuyang Peng, Shishi Xiao, Keming Wu +6
Recently, state-of-the-art text-to-image generation models, such as Flux and Ideogram 2.0, have made significant progress in sentence-level visual text rendering. In this paper, we…
Finite-time ruin probabilities under large-claim reinsurance treaties for heavy-tailed claim sizes
Hansjörg Albrecher, Bohan Chen, Eleni Vatamidou +1
We investigate the probability that an insurance portfolio gets ruined within a finite time period under the assumption that the r largest claims are (partly) reinsured. We show th…
Flow Matching for Efficient and Scalable Data Assimilation
Taos Transue, Bohan Chen, So Takao +1
Data assimilation (DA) estimates a dynamical system's state from noisy observations. Recent generative models like the ensemble score filter (EnSF) improve DA in high-dimensional n…
FontStudio: Shape-Adaptive Diffusion Model for Coherent and Consistent Font Effect Generation
Xinzhi Mu, Li Chen, Bohan Chen +5
Recently, the application of modern diffusion-based text-to-image generation models for creating artistic fonts, traditionally the domain of professional designers, has garnered si…
Consistency of the PLFit estimator for power-law data
Ayan Bhattacharya, Bohan Chen, Remco van der Hofstad +1
We prove the consistency of the Power-Law Fit PLFit method proposed by Clauset et al.(2009) to estimate the power-law exponent in data coming from a distribution function with regu…
Narrative Analysis of True Crime Podcasts With Knowledge Graph-Augmented Large Language Models
Xinyi Leng, Jason Liang, Jack Mauro +8
Narrative data spans all disciplines and provides a coherent model of the world to the reader or viewer. Recent advancement in machine learning and Large Language Models (LLMs) hav…
COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design
Peidong Jia, Chenxuan Li, Yuhui Yuan +10
Graphic design, which has been evolving since the 15th century, plays a crucial role in advertising. The creation of high-quality designs demands design-oriented planning, reasonin…