5 citations · 5 across the 19 of their papers we have counts for
20 papers
Vision: Data-Centric Anchoring for Robust and Interpretable Agentic AI
Arun Vignesh Malarkkan, Xinyuan Wang, Yanjie Fu
Agentic AI systems built on large language models fail in two persistent ways that scaling does not fix: they break under distribution shift, and they cannot explain the decisions…
Causally-Guided Diffusion for Stable Feature Selection
Arun Vignesh Malarkkan, Xinyuan Wang, Kunpeng Liu +2
Feature selection is fundamental to robust data-centric AI, but most existing methods optimize predictive performance under a single data distribution. This often selects spurious…
BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning
Yuan Li, Bo Wang, Yufei Gao +4
Proximal constraints are fundamental to the stability of the Large Language Model reinforcement learning. While the canonical clipping mechanism in PPO serves as an efficient surro…
Evolving Demonstration Optimization for Chain-of-Thought Feature Transformation
Xinyuan Wang, Kunpeng Liu, Arun Vignesh Malarkkan +1
Feature Transformation (FT) is a core data-centric AI task that improves feature space quality to advance downstream predictive performance. However, discovering effective transfor…
Data-Efficient Symbolic Regression via Foundation Model Distillation
Wangyang Ying, Jinghan Zhang, Haoyue Bai +5
Discovering interpretable mathematical equations from observed data (a.k.a. equation discovery or symbolic regression) is a cornerstone of scientific discovery, enabling transparen…
Distribution Shift Aware Neural Tabular Learning
Wangyang Ying, Nanxu Gong, Dongjie Wang +5
Tabular learning transforms raw features into optimized spaces for downstream tasks, but its effectiveness deteriorates under distribution shifts between training and testing data.…
Rethinking Spatio-Temporal Anomaly Detection: A Vision for Causality-Driven Cybersecurity
Arun Vignesh Malarkkan, Haoyue Bai, Xinyuan Wang +3
As cyber-physical systems grow increasingly interconnected and spatially distributed, ensuring their resilience against evolving cyberattacks has become a critical priority. Spatio…
Supply Chain Optimization via Generative Simulation and Iterative Decision Policies
Haoyue Bai, Haoyu Wang, Nanxu Gong +4
High responsiveness and economic efficiency are critical objectives in supply chain transportation, both of which are influenced by strategic decisions on shipping mode. An integra…
LLM-ML Teaming: Integrated Symbolic Decoding and Gradient Search for Valid and Stable Generative Feature Transformation
Xinyuan Wang, Haoyue Bai, Nanxu Gong +4
Feature transformation enhances data representation by deriving new features from the original data. Generative AI offers potential for this task, but faces challenges in stable ge…
PageLLM: A Multi-Grained Reward Framework for Whole-Page Optimization with Large Language Models
Xinyuan Wang, Liang Wu, Dongjie Wang +1
Whole-page optimization (WPO) decides how search and recommendation results are surfaced to users, and large language models (LLMs) open a new route to it by treating page generati…
Efficient Post-Training Refinement of Latent Reasoning in Large Language Models
Xinyuan Wang, Dongjie Wang, Wangyang Ying +5
Reasoning is a key component of language understanding in Large Language Models. While Chain-of-Thought prompting enhances performance via explicit intermediate steps, it suffers f…
Brownian Bridge Augmented Surrogate Simulation and Injection Planning for Geological CO Storage
Haoyue Bai, Guodong Chen, Wangyang Ying +7
Geological CO2 storage (GCS) involves injecting captured CO2 into deep subsurface formations to support climate goals. The effective management of GCS relies on adaptive injection…
Bridging the Domain Gap in Equation Distillation with Reinforcement Feedback
Wangyang Ying, Haoyue Bai, Nanxu Gong +4
The data-to-equation (Data2Eqn) task aims to discover interpretable mathematical equations that map observed values to labels, offering physical insights and broad applicability ac…
Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformation
Nanxu Gong, Zijun Li, Sixun Dong +4
Feature Transformation (FT) crafts new features from original ones via mathematical operations to enhance dataset expressiveness for downstream models. However, existing FT methods…
Agentic Feature Augmentation: Unifying Selection and Generation with Teaming, Planning, and Memories
Nanxu Gong, Sixun Dong, Haoyue Bai +3
As a widely-used and practical tool, feature engineering transforms raw data into discriminative features to advance AI model performance. However, existing methods usually apply f…
Unsupervised Feature Transformation via In-context Generation, Generator-critic LLM Agents, and Duet-play Teaming
Nanxu Gong, Xinyuan Wang, Wangyang Ying +4
Feature transformation involves generating a new set of features from the original dataset to enhance the data's utility. In certain domains like material performance screening, di…
A Survey on Data-Centric AI: Tabular Learning from Reinforcement Learning and Generative AI Perspective
Wangyang Ying, Cong Wei, Nanxu Gong +7
Tabular data is one of the most widely used data formats across various domains such as bioinformatics, healthcare, and marketing. As artificial intelligence moves towards a data-c…
Towards Data-Centric AI: A Comprehensive Survey of Traditional, Reinforcement, and Generative Approaches for Tabular Data Transformation
Dongjie Wang, Yanyong Huang, Wangyang Ying +11
Tabular data is one of the most widely used formats across industries, driving critical applications in areas such as finance, healthcare, and marketing. In the era of data-centric…
Knockoff-Guided Feature Selection via A Single Pre-trained Reinforced Agent
Xinyuan Wang, Dongjie Wang, Wangyang Ying +3
Feature selection prepares the AI-readiness of data by eliminating redundant features. Prior research falls into two primary categories: i) Supervised Feature Selection, which iden…
LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations
Xinyuan Wang, Liang Wu, Liangjie Hong +2
Graph recommendation methods, representing a connected interaction perspective, reformulate user-item interactions as graphs to leverage graph structure and topology to recommend a…