3 papers
cs.LG2026
Where to Start, How to Move: Analyzing Curricula under GRPO for Long-Horizon LLM Agents
Minchan Kim, Sungho Bae, Youngjin Kim +1
Group Relative Policy Optimization (GRPO) provides no reward-relative learning signal when all rollouts receive identical rewards. In long-horizon tasks that require multiple inter…
cs.LG2026
Redefining Maritime Anomaly Detection via Equation-Grounded Synthetic Anomalies
Youngseok Hwang, Sungho Bae, Dohun Lee +4
Maritime anomaly detection is essential for ensuring maritime safety, security, and efficient traffic management at sea, with Automatic Identification System (AIS) data serving as…
cs.LG2025
Spatio-Temporal Graphs Beyond Grids: Benchmark for Maritime Anomaly Detection
Jeehong Kim, Youngseok Hwang, Minchan Kim +2
Spatio-temporal graph neural networks (ST-GNNs) have achieved notable success in structured domains such as road traffic and public transportation, where spatial entities can be na…