A Merged Model under Dual Dynamics Protection
Abstract
Merging abilities changes representations, while dual robustness distinguishes training and deployment dynamics. Evaluation should vary these interventions separately and retain grounded task outcomes. A stable average after merging does not establish protection under both shifts. Independent interactive checks are required to determine whether the combined system preserves useful actions under the declared uncertainty. This focused synthesis develops an empirical comparison that preserves the terminal action, observation process, and total verification cost. Its proposed tests are prospective; no new simulation run, model-training result, or intervention effect is reported.
References
Z. Qiao, R. Yang, J. Lyu, X. Li, Z. Dai, Z. Yang, S. Gao, and S. Qiu, “Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts,” Proceedings of the 2026 International Conference on Learning Representations, 2026.
S. Chen, J. Zhang, T. Zhu, W. Liu, S. Gao, M. Xiong, M. Li, and J. He, “Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging,” Proceedings of the 42nd International Conference on Machine Learning, 2025.
Zhou, Yongxi, Junwei Yao, Yuanzhe Liu, Zihan Dong, Wenbo Ye, Jiaxi Wen, and Lai Yun Choi. “Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity.” arXiv, 2026, arXiv:2608.02665. https://arxiv.org/abs/2608.02665.
Hu, Edward J., et al. “LoRA: Low-Rank Adaptation of Large Language Models.” International Conference on Learning Representations, 2022. https://openreview.net/forum?id=nZeVKeeFYf9.
Guo, Chuan, Geoff Pleiss, Yu Sun, and Kilian Q. Weinberger. “On Calibration of Modern Neural Networks.” Proceedings of the 34th International Conference on Machine Learning, PMLR, vol. 70, 2017, pp. 1321–1330. https://proceedings.mlr.press/v70/guo17a.html.
Sutton, Richard S., and Andrew G. Barto. Reinforcement Learning: An Introduction. 2nd ed., MIT Press, 2018. http://incompleteideas.net/book/the-book-2nd.html.
Levine, Sergey, Aviral Kumar, George Tucker, and Justin Fu. “Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems.” arXiv, 2020, arXiv:2005.01643. https://arxiv.org/abs/2005.01643.
Kumar, Aviral, Aurick Zhou, George Tucker, and Sergey Levine. “Conservative Q-Learning for Offline Reinforcement Learning.” Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 1179–1191. https://arxiv.org/abs/2006.04779.
Lewis, Patrick, et al. “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.” Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 9459–9474. https://arxiv.org/abs/2005.11401.
Geifman, Yonatan, and Ran El-Yaniv. “Selective Classification for Deep Neural Networks.” Advances in Neural Information Processing Systems, vol. 30, 2017. https://arxiv.org/abs/1705.08500.
Ovadia, Yaniv, et al. “Can You Trust Your Model’s Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift.” Advances in Neural Information Processing Systems, vol. 32, 2019. https://arxiv.org/abs/1906.02530.
Published
Versions
- 2026-10-15 (2)
- 2026-05-09 (1)