The paper introduces Align‑LoRA, a unified LoRA framework for multi‑task learning that replaces complex, isolated adapter designs with a single‑adapter model enhanced by a higher rank and an explicit alignment loss. It demonstrates that a router‑free, multi‑head model with high inter‑head redundancy can outperform more elaborate baselines, and that a unified LoRA can achieve competitive performance while enabling weight merging and zero inference latency. Extensive experiments and theoretical analysis confirm that Align‑LoRA surpasses prevailing approaches, offering a simpler, production‑friendly paradigm for parameter‑efficient fine‑tuning of large language models.
By Jinda Liu, Yi Chang, Yuan Wu
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
As large language models (LLMs) scale rapidly, dense full-parameter adaptation becomes increasingly expensive, motivating sparse and modular architectures such as Mixture-of-Experts (MoE) models. This...
The paper introduces EoupCT, a framework that estimates and orthogonalizes unknown pre‑training gradients to mitigate catastrophic forgetting during continual fine‑tuning of large language models. It generates pseudo data most susceptible to forgetting using a learnable soft prompt with Gumbel‑Softmax, then jointly optimizes model parameters and the prompt via a first‑order Pareto optimizer to enforce orthogonality between new task updates and the estimated gradients. Experiments on multiple LLMs show that EoupCT preserves both task‑specific performance and the models’ inherent general‑purpose knowledge.
By Bing Wang, Changchun Li, Xin-Qiang Cai, Lin Yuanbo Wu, Ximing Li, Gang Niu, Masashi Sugiyama
arXiv:2606. 14970v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse downstream tasks and domain-specific data.
By Dmitriy Bystrov, Daniil Medyakov, Dmitry Bylinkin, Aleksandr Beznosikov
arXiv:2609.25655v1 Announce Type: new
Abstract: As large language models (LLMs) scale rapidly, dense full-parameter adaptation becomes increasingly expensive, motivating sparse and modular architectu...
By Zhentao Tan, Chang Liu, Yao Liu, Yue Wu, Jieping Ye
CRAM (Centroid‑Routing and Adaptive MoE) is a method for Multimodal Continual Instruction Tuning that isolates task‑specific patterns into independent modules to reduce catastrophic forgetting. It uses adaptive‑rank instantiation to allocate only the necessary parameters for new tasks, and centroid‑guided routing with an orthogonality penalty to reuse existing experts while preventing interference. Experiments on diverse benchmarks show CRAM outperforms existing approaches.
By Jun-Tao Tang, Zhen-Hao Xie, Yu-Cheng Shi, Da-Wei Zhou
arXiv:2604. 26170v2 Announce Type: replace Abstract: Adapting large language models (LLMs) to a targeted task efficiently and effectively remains a fundamental challenge.
By Ting-Wei Li, Sirui Chen, Jiaru Zou, Yingbing Huang, Tianxin Wei, Jingrui He, Hanghang Tong
The paper introduces task-informed parameter-efficient fine-tuning methods for low-resource speech recognition by applying Fisher-Whitened Cross-Covariance Analysis (FCCA) to Whisper and Qwen3-ASR. Two extensions—Asymmetric-Coupled FCCA (AC‑FCCA) and Adaptive‑Rank FCCA (AR‑FCCA)—are proposed to exploit cross‑layer sharing and adapt rank allocation within a fixed parameter budget. Experiments on multilingual datasets show that standard FCCA matches or surpasses LoRA, while AR‑FCCA consistently improves performance across models without increasing trainable parameters.
By Asmee Mishra, Mengjie Qian, Brechtje Post, Kate Knill
arXiv:2607. 02010v1 Announce Type: new Abstract: Multimodal large language models must adapt to evolving tasks and domains, yet continual improvement under bounded deployment footprint remains difficult because repeated parameter updates or growing replay stores can accumulate adaptation state over time.
By Qianyu Chen, Ziteng Feng, Canran Xiao, Runxuan Tang
arXiv:2608. 13069v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants.
By Lucia Mal\'i\v{c}kov\'a
Multimodal large language models must adapt to evolving tasks and domains, yet continual improvement under bounded deployment footprint remains difficult because repeated parameter updates or growing replay stores can accumulate adaptation state over time. We study fixed-footprint continual adaptation: the deployed adaptation state is kept under a fixed memory budget, while the backbone model is left unchanged and task-specific updates are externalized.