{"ID":2859041,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.07562","arxiv_id":"2510.07562","title":"EBGAN-MDN: An Energy-Based Adversarial Framework for Multi-Modal Behavior Cloning","abstract":"Multi-modal behavior cloning faces significant challenges due to mode averaging and mode collapse, where traditional models fail to capture diverse input-output mappings. This problem is critical in applications like robotics, where modeling multiple valid actions ensures both performance and safety. We propose EBGAN-MDN, a framework that integrates energy-based models, Mixture Density Networks (MDNs), and adversarial training. By leveraging a modified InfoNCE loss and an energy-enforced MDN loss, EBGAN-MDN effectively addresses these challenges. Experiments on synthetic and robotic benchmarks demonstrate superior performance, establishing EBGAN-MDN as a effective and efficient solution for multi-modal learning tasks.","short_abstract":"Multi-modal behavior cloning faces significant challenges due to mode averaging and mode collapse, where traditional models fail to capture diverse input-output mappings. This problem is critical in applications like robotics, where modeling multiple valid actions ensures both performance and safety. We propose EBGAN-M...","url_abs":"https://arxiv.org/abs/2510.07562","url_pdf":"https://arxiv.org/pdf/2510.07562v1","authors":"[\"Yixiao Li\",\"Julia Barth\",\"Thomas Kiefer\",\"Ahmad Fraij\"]","published":"2025-10-08T21:18:01Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}