56 citations · 104 across the 43 of their papers we have counts for
47 papers
Unique Ergodicity for Strongly Damped Stochastic Wave Equations under Finite-Rank Pure-Jump Lévy Forcing
Jiangwei Zhang, Jianhua Huang
We study a strongly damped stochastic wave equation on the three-dimensional torus driven by finite-rank pure-jump Lévy noise obtained from subordinated Brownian motion. Lyapunov e…
Self-Consuming Generative Models with Co-Evolving Human Preferences
Xiukun Wei, Tian Xie, Ding Zhu +1
Generative models are increasingly trained in self-consuming iterative loops, where users curate preferred samples from model-generated candidates and the curated samples are used…
When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs
Suchit Gupte, Xueru Zhang, Mohammad Mahdi Khalili
Sparse autoencoders (SAEs) are widely used to interpret the internal representations of large language models (LLMs), yet their reliability under post-hoc model compression remains…
BRAID: Learning Equilibrium Maps in Interdependent Security Games via Weight-Tied Iterative Graph Neural Networks
Elnaz Nowrouzi, Zhiqun Zuo, Xueru Zhang +1
Computing Nash equilibria in interdependent security (IDS) games on networks is computationally expensive: best-response dynamics may need hundreds of iterations per instance, and…
TLRD: Teaching LLMs to Reason over Tabular Data with Tri-Level Rationale Distillation
Tianyuan Liang, Xuwei Tan, Lei Shi +6
Tabular data is a primary medium for storing real-world information, driving many industrial applications of machine learning. Traditional predictors achieve strong predictive perf…
PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA
Shihao Wang, Xueru Zhang
Applying differential privacy (DP) via DP-SGD to Low-Rank Adaptation (LoRA) is a natural approach for privacy-preserving fine-tuning. However, LoRA's low-rank parameterization pose…
When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming Loop
Yang Zhang, Xiukun Wei, Xueru Zhang
Foundation models are increasingly trained on synthetic data generated by prior model iterations rather than exclusively on real data. This self-consuming training paradigm can lea…
Market Games for Generative Models: Equilibria, Welfare, and Strategic Entry
Xiukun Wei, Min Shi, Xueru Zhang
Generative model ecosystems increasingly operate as competitive multi-platform markets, where platforms strategically select models from a shared pool and users with heterogeneous…
Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs
Xuwei Tan, Ziyu Hu, Xueru Zhang
Machine learning models trained on real-world data often inherit and amplify biases against certain social groups, raising urgent concerns about their deployment at scale. While nu…
Observations and Remedies for Large Language Model Bias in Self-Consuming Performative Loop
Yaxuan Wang, Zhongteng Cai, Yujia Bao +2
The rapid advancement of large language models (LLMs) has led to growing interest in using synthetic data to train future models. However, this creates a self-consuming retraining…
DABench-LLM: Standardized and In-Depth Benchmarking of Post-Moore Dataflow AI Accelerators for LLMs
Ziyu Hu, Zhiqing Zhong, Weijian Zheng +6
The exponential growth of large language models has outpaced the capabilities of traditional CPU and GPU architectures due to the slowdown of Moore's Law. Dataflow AI accelerators…
Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection
Xuwei Tan, Yao Ma, Xueru Zhang
Detecting fraud in financial transactions typically relies on tabular models that demand heavy feature engineering to handle high-dimensional data and offer limited interpretabilit…
Stabilizing Self-Consuming Diffusion Models with Latent Space Filtering
Zhongteng Cai, Yaxuan Wang, Yang Liu +1
As synthetic data proliferates across the Internet, it is often reused to train successive generations of generative models. This creates a ``self-consuming loop" that can lead to…
Achieving Fairness Without Harm via Selective Demographic Experts
Xuwei Tan, Yuanlong Wang, Thai-Hoang Pham +2
As machine learning systems become increasingly integrated into human-centered domains such as healthcare, ensuring fairness while maintaining high predictive performance is critic…
The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective
Thai-Hoang Pham, Jiayuan Chen, Seungyeon Lee +4
As machine learning (ML) algorithms are increasingly used in medical image analysis, concerns have emerged about their potential biases against certain social groups. Although many…
Deep learning for flash drought forecasting and interpretation
Qian Zhao, Xuwei Tan, Xueru Zhang +2
Flash droughts are increasingly occurring worldwide due to climate change, causing widespread socioeconomic and agricultural losses. However, timely and accurate flash drought fore…
Demographic-Agnostic Fairness without Harm
Zhongteng Cai, Mohammad Mahdi Khalili, Xueru Zhang
As machine learning (ML) algorithms are increasingly used in social domains to make predictions about humans, there is a growing concern that these algorithms may exhibit biases ag…
SPRINT: Stochastic Performative Prediction With Variance Reduction
Tian Xie, Ding Zhu, Jia Liu +2
Performative prediction (PP) is an algorithmic framework for optimizing machine learning (ML) models where the model's deployment affects the distribution of the data it is trained…
Self-Consuming Generative Models with Adversarially Curated Data
Xiukun Wei, Xueru Zhang
Recent advances in generative models have made it increasingly difficult to distinguish real data from model-generated synthetic data. Using synthetic data for successive training…
BiasCause: Evaluate Socially Biased Causal Reasoning of Large Language Models
Tian Xie, Tongxin Yin, Vaishakh Keshava +2
While large language models (LLMs) play increasingly significant roles in society, research shows they continue to generate content that reflects social bias against sensitive grou…
How Strategic Agents Respond: Comparing Analytical Models with LLM-Generated Responses in Strategic Classification
Tian Xie, Pavan Rauch, Xueru Zhang
When ML algorithms are deployed to automate human-related decisions, human agents may learn the underlying decision policies and adapt their behavior. Strategic Classification (SC)…
DroughtSet: Understanding Drought Through Spatial-Temporal Learning
Xuwei Tan, Qian Zhao, Yanlan Liu +1
Drought is one of the most destructive and expensive natural disasters, severely impacting natural resources and risks by depleting water resources and diminishing agricultural yie…
Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm
Thai-Hoang Pham, Yuanlong Wang, Changchang Yin +2
Domain adaptation (DA) tackles the issue of distribution shift by learning a model from a source domain that generalizes to a target domain. However, most existing DA methods are d…
Lookahead Counterfactual Fairness
Zhiqun Zuo, Tian Xie, Xuwei Tan +2
As machine learning (ML) algorithms are used in applications that involve humans, concerns have arisen that these algorithms may be biased against certain social groups. \textit{Co…