Gupta et al. "Robust Multi-Objective Preference Alignment with Online DPO." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I26.34942
Markdown
[Gupta et al. "Robust Multi-Objective Preference Alignment with Online DPO." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/gupta2025aaai-robust/) doi:10.1609/AAAI.V39I26.34942
BibTeX
@inproceedings{gupta2025aaai-robust,
title = {{Robust Multi-Objective Preference Alignment with Online DPO}},
author = {Gupta, Raghav and Sullivan, Ryan and Li, Yunxuan and Phatale, Samrat and Rastogi, Abhinav},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {27321-27329},
doi = {10.1609/AAAI.V39I26.34942},
url = {https://mlanthology.org/aaai/2025/gupta2025aaai-robust/}
}