arXiv:2506. 14126v2 Announce Type: replace-cross Abstract: Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets.
By Stefan Horoi, Guy Wolf, Eugene Belilovsky, Gintare Karolina Dziugaite
SMAT (Simple and Efficient Merge-Aware Training) is a method that jointly optimizes expert loss and expected loss at simulated merged parameters, addressing the shortcomings of standard expert training for model merging. It models common merging operations—Scale, Mask, and Perturb—by sampling scaling coefficients, masks, and additive noise, and introduces efficient techniques such as periodic scheduling, kernel fusion, and parameter storage switching to keep training overhead minimal. Across multiple language and vision-language backbones, SMAT improves mean scores by 1.07–2.16 points over the strongest baseline while adding less than 2% training-time overhead.
By Yanggan Gu, Yuanyi Wang, Zhen Li, Shuo Cai, Yuhang Liu, Junzhuo Li, Zihao Wang, Hongxia Yang
ReForge is a bilevel optimization framework that refines merged models by treating module-wise refinement as Bayesian linear regression with an anchor-centered prior. The inner level produces a closed‑form MAP estimate from unlabeled calibration activations, while the outer level employs Bayesian optimization to jointly select regularization strengths and assembly scales using validation data. A data‑free variant replaces activation statistics with task‑vector Grams, enabling refinement without calibration examples, and across extensive vision and language benchmarks ReForge consistently outperforms existing plug‑and‑play anchor baselines, achieving significant accuracy gains on large‑scale tasks such as 20‑task ViT‑B/32 and eight‑task ViT‑L/14.
By Kaiyang Li, Shaobo Han, Qing Su, Shihao Ji
arXiv:2603. 12433v3 Announce Type: replace-cross Abstract: Model stitching, connecting early layers of one model (source) to later layers of another (target) via a light stitch layer, has served as a probe of representational compatibility.
By Zheda Mai, Ke Zhang, Fu-En Wang, Zixiao Ken Wang, Albert Y. C. Chen, Lu Xia, Min Sun, Wei-Lun Chao, Cheng-Hao Kuo
arXiv:2608. 12842v1 Announce Type: new Abstract: Model merging has recently attracted significant attention as a promising paradigm for constructing unified multi-task models without requiring additional retraining.
By Yuchen Liu, Zongzhen Yang, Binhang Qi, Hailong Sun, Xiang Gao
arXiv:2606. 19549v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) makes it cheap to train many domain- and task-specific language model adapters, but whether two adapters can be merged is usually discovered only after both have been fully trained and evaluated.
By Lin Tang, Wei Zhang, Jing Li, Hongyu Chen, Ming Zhao, Yuxuan Wang