DAMO: Decoding by Accumulating Activations Momentum for Mitigating Hallucinations in Vision-Language Models
Published in The Thirteenth International Conference on Learning Representations (ICLR-2025), 2025
Recommended citation: Kaishen Wang, Hengrui Gu, Meijun Gao, Kaixiong Zhou. (2025). "DAMO: Decoding by Accumulating Activations Momentum for Mitigating Hallucinations in Vision-Language Models." Proceedings of the Thirteenth International Conference on Learning Representations (ICLR), 2025.
Download Paper