CtM merges T LoRAs into one rank-r LoRA by computing shared r-dimensional subspaces from the LoRA weights, projecting adapters into r x r coordinates, and merging in that reduced space, outperforming merge-then-compress baselines in experiments.
Revisiting weight averaging for model merging
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
A task-alignment proxy — feature distance between merged and per-task encoders on unlabeled data — selects merging hyperparameters nearly as well as full downstream evaluation, at a fraction of the cost.
ACE-Merging estimates task input covariances from parameter differences to enable closed-form data-free merging that reduces interference and outperforms prior baselines on vision and language tasks.
Kairos learns and maintains control-sufficient world states via a cross-embodiment curriculum, hybrid linear temporal attention, and deployment-aware co-design for Physical AI.
citing papers explorer
-
Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter
CtM merges T LoRAs into one rank-r LoRA by computing shared r-dimensional subspaces from the LoRA weights, projecting adapters into r x r coordinates, and merging in that reduced space, outperforming merge-then-compress baselines in experiments.
-
Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks
A task-alignment proxy — feature distance between merged and per-task encoders on unlabeled data — selects merging hyperparameters nearly as well as full downstream evaluation, at a fraction of the cost.
-
ACE-Merging: Data-Free Model Merging with Adaptive Covariance Estimation
ACE-Merging estimates task input covariances from parameter differences to enable closed-form data-free merging that reduces interference and outperforms prior baselines on vision and language tasks.
-
Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI
Kairos learns and maintains control-sufficient world states via a cross-embodiment curriculum, hybrid linear temporal attention, and deployment-aware co-design for Physical AI.