Woohyung Lim

Vice President@LG AI Research·韩国·OpenReview

研究方向

Causal Inference · Causal Discovery · Anomaly Detection · Reinforcement Learning · Neural Combinatorial Optimization · Recommender System · Table Representation Learning · Machine Learning · Speech Recognition · Time-series Forecasting · Representation Learning · Semu-supervised Learning · Unsupervised Learning

Woohyung Lim

ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection

From Static Benchmarks to Dynamic Protocol: Agent-Centric Text Anomaly Detection for Evaluating LLM Reasoning

Designing Observation and Action Models for Efficient Reinforcement Learning with LLMs

Enhancing Deep Tabular Models with GBDT-Guided Piecewise-Linear Embeddings

TS-TPR: Tensor Product Representation for Multivariate Time Series Forecasting

Attention-Guided Masking and Neighbor-Informed Reconstruction for Tabular Anomaly Detection

Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data

Online Pre-Training for Offline-to-Online Reinforcement Learning

Agent-Centric Actor-Critic for Asynchronous Multi-Agent Reinforcement Learning

Online Pre-Training for Offline-to-Online Reinforcement Learning

CADO: Cost-Aware Diffusion Models for Combinatorial Optimization via RL Fine-tuning

Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data

Range-limited Augmentation for Few-shot Learning in Tabular Data

SteBen: Steiner Tree Problem Benchmark for Neural Combinatorial Optimization on Graphs