20 citations · 31 across the 31 of their papers we have counts for
33 papers
Flat-Consensus Diffusion for Robust Data Reshaping under Noisy Evaluator
Hongyu Cao, Kunpeng Liu, Fei Xie +1
Data shape determines how features are structured, how patterns are separated, and how distributions cover the underlying domain. Poor data shape can make models learn noise rather…
StaRPO: Stability-Augmented Reinforcement Policy Optimization
Jinghan Zhang, Fengran Mo, Tharindu Cyril Weerasooriya +5
Reinforcement learning (RL) is effective in enhancing the accuracy of large language models in complex reasoning tasks. Existing RL policy optimization frameworks rely on final-ans…
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…
Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach
Hongyu Cao, Kunpeng Liu, Dongjie Wang +1
Large language models exhibit strong reasoning capabilities, yet often rely on shortcuts such as surface pattern matching and answer memorization rather than genuine logical infere…
AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem
Rui Liu, Tao Zhe, Dongjie Wang +5
The rapid emergence of open-source, locally hosted intelligent agents marks a critical inflection point in human-computer interaction. Systems such as OpenClaw demonstrate that Lar…
Sim2Act: Robust Simulation-to-Decision Learning via Adversarial Calibration and Group-Relative Perturbation
Hongyu Cao, Jinghan Zhang, Kunpeng Liu +5
Simulation-to-decision learning enables safe policy training in digital environments without risking real-world deployment, and has become essential in mission-critical domains suc…
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…
City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modification
Rui Liu, Steven Jige Quan, Zhong-Ren Peng +6
Urban renewal requires incremental modifications to existing geospatial plans, yet manually updating complex layouts under spatial constraints is labor-intensive and error-prone. T…
Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation
Tao Zhe, Huazhen Fang, Kunpeng Liu +3
Feature transformation enhances downstream task performance by generating informative features through mathematical feature crossing. Despite the advancements in deep learning, fea…
Dataforge: Agentic Platform for Autonomous Data Engineering
Xinyuan Wang, Hongyu Cao, Kunpeng Liu +1
The growing demand for artificial intelligence (AI) applications in materials discovery, molecular modeling, and climate science has made data preparation a critical but labor-inte…
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…
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…
Iterative Feature Space Optimization through Incremental Adaptive Evaluation
Yanping Wu, Yanyong Huang, Zhengzhang Chen +5
Iterative feature space optimization involves systematically evaluating and adjusting the feature space to improve downstream task performance. However, existing works suffer from…
Topology-aware Reinforcement Feature Space Reconstruction for Graph Data
Wangyang Ying, Haoyue Bai, Kunpeng Liu +1
Feature space is an environment where data points are vectorized to represent the original dataset. Reconstructing a good feature space is essential to augment the AI power of data…
Enhanced Gene Selection in Single-Cell Genomics: Pre-Filtering Synergy and Reinforced Optimization
Weiliang Zhang, Zhen Meng, Dongjie Wang +4
Recent advancements in single-cell genomics necessitate precision in gene panel selection to interpret complex biological data effectively. Those methods aim to streamline the anal…
A Comprehensive Survey on Data Augmentation
Zaitian Wang, Pengfei Wang, Kunpeng Liu +6
Data augmentation is a series of techniques that generate high-quality artificial data by manipulating existing data samples. By leveraging data augmentation techniques, AI models…
Self-optimizing Feature Generation via Categorical Hashing Representation and Hierarchical Reinforcement Crossing
Wangyang Ying, Dongjie Wang, Kunpeng Liu +2
Feature generation aims to generate new and meaningful features to create a discriminative representation space.A generated feature is meaningful when the generated feature is from…
Feature Interaction Aware Automated Data Representation Transformation
Ehtesamul Azim, Dongjie Wang, Kunpeng Liu +2
Creating an effective representation space is crucial for mitigating the curse of dimensionality, enhancing model generalization, addressing data sparsity, and leveraging classical…
Traceable Group-Wise Self-Optimizing Feature Transformation Learning: A Dual Optimization Perspective
Meng Xiao, Dongjie Wang, Min Wu +4
Feature transformation aims to reconstruct an effective representation space by mathematically refining the existing features. It serves as a pivotal approach to combat the curse o…
A Counterfactual Collaborative Session-based Recommender System
Wenzhuo Song, Shoujin Wang, Yan Wang +3
Most session-based recommender systems (SBRSs) focus on extracting information from the observed items in the current session of a user to predict a next item, ignoring the causes…
Traceable Automatic Feature Transformation via Cascading Actor-Critic Agents
Meng Xiao, Dongjie Wang, Min Wu +5
Feature transformation for AI is an essential task to boost the effectiveness and interpretability of machine learning (ML). Feature transformation aims to transform original data…
Mitigating Popularity Bias in Recommendation with Unbalanced Interactions: A Gradient Perspective
Weijieying Ren, Lei Wang, Kunpeng Liu +3
Recommender systems learn from historical user-item interactions to identify preferred items for target users. These observed interactions are usually unbalanced following a long-t…
Automated Urban Planning aware Spatial Hierarchies and Human Instructions
Dongjie Wang, Kunpeng Liu, Yanyong Huang +3
Traditional urban planning demands urban experts to spend considerable time and effort producing an optimal urban plan under many architectural constraints. The remarkable imaginat…
Self-Optimizing Feature Transformation
Meng Xiao, Dongjie Wang, Min Wu +4
Feature transformation aims to extract a good representation (feature) space by mathematically transforming existing features. It is crucial to address the curse of dimensionality,…