60 citations · 132 across the 25 of their papers we have counts for
25 papers
Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
Rongzhi Zhang, Liqin Ye, Yuzhao Heng +5
Precise attribute intensity control--generating Large Language Model (LLM) outputs with specific, user-defined attribute intensities--is crucial for AI systems adaptable to diverse…
Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process
Lingkai Kong, Haotian Sun, Yuchen Zhuang +3
Graph neural networks (GNNs) are powerful tools on graph data. However, their predictions are mis-calibrated and lack interpretability, limiting their adoption in critical applicat…
LLM-Augmented Chemical Synthesis and Design Decision Programs
Haorui Wang, Jeff Guo, Lingkai Kong +4
Retrosynthesis, the process of breaking down a target molecule into simpler precursors through a series of valid reactions, stands at the core of organic chemistry and drug develop…
Learning Graph Structures and Uncertainty for Accurate and Calibrated Time-series Forecasting
Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodriguez +2
Multi-variate time series forecasting is an important problem with a wide range of applications. Recent works model the relations between time-series as graphs and have shown that…
Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning
Haoxin Liu, Harshavardhan Kamarthi, Lingkai Kong +3
Time-series forecasting (TSF) finds broad applications in real-world scenarios. Due to the dynamic nature of time-series data, it is crucial to equip TSF models with out-of-distrib…
Efficient Evolutionary Search Over Chemical Space with Large Language Models
Haorui Wang, Marta Skreta, Cher-Tian Ser +11
Molecular discovery, when formulated as an optimization problem, presents significant computational challenges because optimization objectives can be non-differentiable. Evolutiona…
Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis
Haoxin Liu, Shangqing Xu, Zhiyuan Zhao +8
Time series data are ubiquitous across a wide range of real-world domains. While real-world time series analysis (TSA) requires human experts to integrate numerical series data wit…
Aligning Large Language Models with Representation Editing: A Control Perspective
Lingkai Kong, Haorui Wang, Wenhao Mu +7
Aligning large language models (LLMs) with human objectives is crucial for real-world applications. However, fine-tuning LLMs for alignment often suffers from unstable training and…
Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints
Lingkai Kong, Yuanqi Du, Wenhao Mu +8
Addressing real-world optimization problems becomes particularly challenging when analytic objective functions or constraints are unavailable. While numerous studies have addressed…
TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance
Haorui Wang, Rongzhi Zhang, Yinghao Li +4
Large Language Models (LLMs) have recently showcased remarkable reasoning abilities. However, larger models often surpass their smaller counterparts in reasoning tasks, posing the…
When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting
Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodríguez +2
Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting, where the goal is to model and forecast multivariate time-series that have un…
DF2: Distribution-Free Decision-Focused Learning
Lingkai Kong, Wenhao Mu, Jiaming Cui +4
Decision-focused learning (DFL), which differentiates through the KKT conditions, has recently emerged as a powerful approach for predict-then-optimize problems. However, under pro…
Autoregressive Diffusion Model for Graph Generation
Lingkai Kong, Jiaming Cui, Haotian Sun +3
Diffusion-based graph generative models have recently obtained promising results for graph generation. However, existing diffusion-based graph generative models are mostly one-shot…
DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling
Yuchen Zhuang, Yue Yu, Lingkai Kong +2
Learning from noisy labels is a challenge that arises in many real-world applications where training data can contain incorrect or corrupted labels. When fine-tuning language model…
MUBen: Benchmarking the Uncertainty of Molecular Representation Models
Yinghao Li, Lingkai Kong, Yuanqi Du +4
Large molecular representation models pre-trained on massive unlabeled data have shown great success in predicting molecular properties. However, these models may tend to overfit t…
AdaPlanner: Adaptive Planning from Feedback with Language Models
Haotian Sun, Yuchen Zhuang, Lingkai Kong +2
Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. However, most existing methods either tak…
End-to-End Stochastic Optimization with Energy-Based Model
Lingkai Kong, Jiaming Cui, Yuchen Zhuang +3
Decision-focused learning (DFL) was recently proposed for stochastic optimization problems that involve unknown parameters. By integrating predictive modeling with an implicitly di…
When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting
Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodríguez +2
Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting, where the goal is to model and forecast multivariate time-series that have un…
Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport
Lingkai Kong, Yuqing Wang, Molei Tao
The problem of optimization on Stiefel manifold, i.e., minimizing functions of (not necessarily square) matrices that satisfy orthogonality constraints, has been extensively studie…
AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language Models
Yue Yu, Lingkai Kong, Jieyu Zhang +2
While pre-trained language model (PLM) fine-tuning has achieved strong performance in many NLP tasks, the fine-tuning stage can be still demanding in labeled data. Recent works hav…
CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting
Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodríguez +2
Probabilistic time-series forecasting enables reliable decision making across many domains. Most forecasting problems have diverse sources of data containing multiple modalities an…
When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting
Harshavardhan Kamarthi, Lingkai Kong, Alexander Rodríguez +2
Accurate and trustworthy epidemic forecasting is an important problem that has impact on public health planning and disease mitigation. Most existing epidemic forecasting models di…
Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data
Lingkai Kong, Haoming Jiang, Yuchen Zhuang +3
Fine-tuned pre-trained language models can suffer from severe miscalibration for both in-distribution and out-of-distribution (OOD) data due to over-parameterization. To mitigate t…
SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates
Lingkai Kong, Jimeng Sun, Chao Zhang
Uncertainty quantification is a fundamental yet unsolved problem for deep learning. The Bayesian framework provides a principled way of uncertainty estimation but is often not scal…