7 papers
A Unified Generalization Framework for Model Merging: Trade-offs, Non-Linearity, and Scaling Laws
Qinglun Li, Anke Tang, Miao Zhang +3
Model merging efficiently aggregates capabilities from multiple fine-tuned models into a single one, operating purely in parameter space without original data or expensive re-compu…
ACE-Brain-0: Spatial Intelligence as a Shared Scaffold for Universal Embodiments
Ziyang Gong, Zehang Luo, Anke Tang +21
Universal embodied intelligence demands robust generalization across heterogeneous embodiments, such as autonomous driving, robotics, and unmanned aerial vehicles (UAVs). However,…
OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging
Yongxian Wei, Runxi Cheng, Weike Jin +7
Foundation models update slowly due to resource-intensive training, whereas domain-specific models evolve rapidly between releases. Model merging seeks to combine multiple expert m…
Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
Jinluan Yang, Dingnan Jin, Anke Tang +10
Achieving balanced alignment of large language models (LLMs) in terms of Helpfulness, Honesty, and Harmlessness (3H optimization) constitutes a cornerstone of responsible AI. Exist…
Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
Yongxian Wei, Anke Tang, Li Shen +3
Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data. Existing methods attempt to alleviate task conf…
Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace
Jinluan Yang, Anke Tang, Didi Zhu +3
Model merging has gained significant attention as a cost-effective approach to integrate multiple single-task fine-tuned models into a unified one that can perform well on multiple…