The paper introduces READ, a method for composing low‑rank adapters (LoRA) in large language models. By rewriting each adapter into a balanced canonical form and enforcing a one‑directional coupling, READ allows new skills to read but never write into the output subspaces of existing skills, eliminating interference. Experiments on four benchmark suites and two model families show that READ consistently outperforms existing baselines, improving SuperGLUE scores by over twenty points and domain suite scores by more than seven points.
By Zeyan Li, Panqi Yang, Qirong Guo, Shengda Zhuo, SIyuan Qiu, Hu Xu, Chun Li, Jianfeng Xu
CAMFT is a Conflict‑Aware Mergeable Fine‑Tuning method designed to make task adaptation efficient and merge‑aware for large language models. Unlike existing approaches that only resolve parameter conflicts after fine‑tuning, CAMFT shapes mergeability during training by guiding each task to update sparse coordinates with lower cross‑task conflict. Experiments show that CAMFT outperforms standard fine‑tuning baselines in multi‑task merging scenarios.
By Jingang Zhou, Haiyang Guo, Yuan Ma, Han Zhu, Xu-Yao Zhang
arXiv:2607. 20561v1 Announce Type: new Abstract: LoRA adapters provide an efficient way to specialize a pretrained model for many downstream tasks, but deploying one adapter per task requires adapter storage and task selection at inference time.
By Keumseo Ryum, Joonhyuk Kang
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:2608.31096v1 Announce Type: cross
Abstract: Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while...
By Yunxiang Fu, Meng Lou, Yizhou Yu
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
arXiv:2606. 18627v1 Announce Type: new Abstract: Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model.
By Ningyuan Shi, Zhipeng Zhou, Hao Wang, Chunyan Miao, Peilin Zhao
arXiv:2605.07111v3 Announce Type: replace-cross
Abstract: Recent literature on fine-tuning Large Language Models highlights a fundamental debate. While Full Fine-Tuning (FFT) provides greater represe...
By Haozhan Tang, Xiuqi Zhu, Xinyin Zhang, Boxun Li, Virginia Smith, Kevin Kuo
arXiv:2602. 12323v2 Announce Type: replace Abstract: The widespread availability of fine-tuned LoRA modules for open pre-trained models has led to an interest in methods that can adaptively merge LoRAs to improve performance.
By Haokun Liu, Gyung Hyun Je, Marco Ciccone, Zhenlin Xu, Prasanth YSS, Colin Raffel
arXiv:2607. 18026v1 Announce Type: new Abstract: Can large language models with substantially different parameter spaces be merged by direct weighted averaging, without training or semantic alignment?
By Jiahe Fan, Yinghao Hou, Si Chen, Aiyuan Zhang, Hong Xie, Defu Lian
UpgradeBench is a decision‑centric longitudinal benchmark that evaluates how fine‑tuned language‑model specialists should be handled when new base‑model releases occur. It covers four consecutive Qwen releases, a continuation checkpoint, six tasks, two model sizes, and OLMo checkpoints with known training lineage, and examines whether retraining, adapter transfer, or other recovery strategies improve specialist performance. The benchmark reveals that upgrade gains vary by task and release interval, that direct adapter copying is sensitive to pretraining distance, and that teacher relabeling can recover specialists without new annotations.
"whyItMatters":"The study provides actionable insights into the cost‑effective management of specialist models across model releases, showing how to balance retraining effort with performance gains."
By Ye Chen, Weining Zhang
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