8 citations · 16 across the 15 of their papers we have counts for
17 papers
Correcting or Continuing? What On-Policy Distillation Learns from Student Errors
Shuo Yang, Zheyu Zhang, Mahito Sugiyama +1
On-policy distillation (OPD) trains a student on its own rollouts under a frozen teacher, mitigating the distribution mismatch of off-policy supervision. While prior work has prima…
Relational Learning as World Modeling
Zheyu Zhang, Gjergji Kasneci
Relational learning typically predicts from a database state, but decision making asks a different question: how will that state change under an action? In operational systems, the…
Consolidating Rewarded Perturbations for LLM Post-Training
Zheyu Zhang, Shuo Yang, Gjergji Kasneci
Post-training of language models is commonly framed as a sample-score-update loop implemented by gradient descent. A recent line of work, exemplified by RandOpt, relocates this loo…
CFG: Control Classifier-Free Guidance via Score Discrepancy Analysis
Jiayang Gao, Tianyi Zheng, Jiayang Zou +9
Classifier-Free Guidance (CFG) is a cornerstone of modern conditional diffusion models, yet its reliance on the fixed or heuristic dynamic guidance weight is predominantly empirica…
Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs
Chenchen Yuan, Bolei Ma, Zheyu Zhang +3
While recent research has systematically documented political orientation in large language models (LLMs), existing evaluations rely primarily on direct probing or demographic pers…
Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs
Shuo Yang, Zheyu Zhang, Bardh Prenkaj +1
Tabular data is critical across diverse domains, yet high-quality datasets remain scarce due to privacy concerns and the cost of collection. Contemporary approaches adopt large lan…
Goal-Oriented Sequential Bayesian Experimental Design for Causal Learning
Zheyu Zhang, Jiayuan Dong, Jie Liu +1
We present GO-CBED, a goal-oriented Bayesian framework for sequential causal experimental design. Unlike conventional approaches that select interventions aimed at inferring the fu…
Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models
Zheyu Zhang, Shuo Yang, Bardh Prenkaj +1
Large Language Models (LLMs) have shown strong potential for tabular data generation by modeling textualized feature-value pairs. However, tabular data inherently exhibits sparse f…
Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
Chenchen Yuan, Zheyu Zhang, Shuo Yang +2
Large Language Models (LLMs) have shown impressive moral reasoning abilities. Yet they often diverge when confronted with complex, multi-factor moral dilemmas. To address these dis…
MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning
Suning Huang, Zheyu Zhang, Tianhai Liang +6
Visual deep reinforcement learning (RL) enables robots to acquire skills from visual input for unstructured tasks. However, current algorithms suffer from low sample efficiency, li…
Reinforcement Learning-Based Approaches for Enhancing Security and Resilience in Smart Control: A Survey on Attack and Defense Methods
Zheyu Zhang
Reinforcement Learning (RL), one of the core paradigms in machine learning, learns to make decisions based on real-world experiences. This approach has significantly advanced AI ap…
Autonomous Tree-search Ability of Large Language Models
Zheyu Zhang, Zhuorui Ye, Yikang Shen +1
Large Language Models have excelled in remarkable reasoning capabilities with advanced prompting techniques, but they fall short on tasks that require exploration, strategic foresi…
ModuleFormer: Modularity Emerges from Mixture-of-Experts
Yikang Shen, Zheyu Zhang, Tianyou Cao +3
Large Language Models (LLMs) have achieved remarkable results. However, existing models are expensive to train and deploy, and it is also difficult to expand their knowledge beyond…
Unbiased Gradient Boosting Decision Tree with Unbiased Feature Importance
Zheyu Zhang, Tianping Zhang, Jian Li
Gradient Boosting Decision Tree (GBDT) has achieved remarkable success in a wide variety of applications. The split finding algorithm, which determines the tree construction proces…
Indoor room Occupancy Counting based on LSTM and Environmental Sensor
Zheyu Zhang
This paper realizes the estimation of classroom occupancy by using the CO2 sensor and deep learning technique named Long-Short-Term Memory. As a case of connection with IoT and mac…
OpenFE: Automated Feature Generation with Expert-level Performance
Tianping Zhang, Zheyu Zhang, Zhiyuan Fan +5
The goal of automated feature generation is to liberate machine learning experts from the laborious task of manual feature generation, which is crucial for improving the learning p…
Tabletop Object Rearrangement: Team ACRV's Entry to OCRTOC
Zheyu Zhang, Rhys Newbury, Kerry He +5
Open Cloud Robot Table Organization Challenge (OCRTOC) is one of the most comprehensive cloud-based robotic manipulation competitions. It focuses on rearranging tabletop objects us…