Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain underexplored. In this paper, we provide several insights into such fine-tuning through the lens of linearization. Fine-tuned models are often implicitly encouraged to remain close to the pretrained model. By making this explicit, using an ℓ2distance inductive bias in parameter space, we show that fine-tuning dynamics become equivalent to learning with the positive-definite neural tangent kernel (NTK). We specifically analyze how close the fully linear and the linearized finetuning optimizations are, based on the strength of the regularization. This allows us to be pragmatic about how good a model linearization is when fine-tuning large language models (LLMs). When linearization is a good model, our findings reveal a strong correlation between the eigenvalue spectrum of the NTK and the performance of model adaptation. Motivated by this, we give spectral perturbation bounds on the NTK induced by the choice of layers selected for fine-tuning.

Foundation models (FMs) are pre-trained on large-scale datasets and then finetuned for a specific downstream task. The most common fine-tuning method is to update pretrained weights via low-rank adaptation (LoRA). Existing initialization strategies for LoRA often rely on singular value decompositions (SVD) of gradients or weight matrices. However, they do not provably maximize the expected gradient signal, which is critical for fast adaptation. To this end, we introduce Explained Variance Adaptation (EVA), an initialization scheme that uses the directions capturing the most activation variance, provably maximizing the expected gradient signal and accelerating fine-tuning.

Low-Rank Adaptation (LoRA) has become the de facto parameter-efficient finetuning (PEFT) method for large language models (LLMs) by constraining weight updates to low-rank matrices. Recent works such as Tied-LoRA, VeRA, and VBLoRA push efficiency further by introducing additional constraints to reduce the trainable parameter space. In this paper, we show that the parameter space reduction strategies employed by these LoRA variants can be formulated within a unified framework, Uni-LoRA, where the LoRA parameter space, flattened as a highdimensional vector space RD, can be reconstructed through a projection from a subspace Rd, with d D. We demonstrate that the fundamental difference among various LoRA methods lies in the choice of the projection matrix, P RD d. Most existing LoRA variants rely on layer-wise or structure-specific projections that limit cross-layer parameter sharing, thereby compromising parameter efficiency. In light of this, we introduce an efficient and theoretically grounded projection matrix that is isometric, enabling global parameter sharing and reducing computation overhead. Furthermore, under the unified view of Uni-LoRA, this design requires only a single trainable vector to reconstruct LoRA parameters for the entire LLM - making UniLoRA both a unified framework and a "one-vector-only" solution. Extensive experiments on GLUE, mathematical reasoning, and instruction tuning benchmarks demonstrate that Uni-LoRA achieves state-of-the-art parameter efficiency while outperforming or matching prior approaches in predictive performance.

In this paper, we propose AdaMSS, an adaptive multi-subspace approach for parameter-efficient fine-tuning of large models. Unlike traditional parameterefficient fine-tuning methods that operate within a large single subspace of the network weights, AdaMSS leverages subspace segmentation to obtain multiple smaller subspaces and adaptively reduces the number of trainable parameters during training, ultimately updating only those associated with a small subset of subspaces most relevant to the target downstream task. By using the lowest-rank representation, AdaMSS achieves more compact expressiveness and finer tuning of the model parameters. Theoretical analyses demonstrate that AdaMSS has better generalization guarantee than LoRA, PiSSA, and other single-subspace low-rankbased methods. Extensive experiments across image classification, natural language understanding, and natural language generation tasks show that AdaMSS achieves comparable performance to full fine-tuning and outperforms other parameterefficient fine-tuning methods in most cases, all while requiring fewer trainable parameters. Notably, on the ViT-Large model, AdaMSS achieves 4.7% higher average accuracy than LoRA across seven tasks, using just 15.4% of the trainable parameters. On RoBERTa-Large, AdaMSS outperforms PiSSA by 7% in average accuracy across six tasks while reducing the number of trainable parameters by approximately 94.4%. These results demonstrate the effectiveness of AdaMSS in parameter-efficient fine-tuning. The code for AdaMSS is available at https: //github.com/jzheng20/AdaMSS.

In this paper, we propose AdaMSS, an adaptive multi-subspace approach for parameter-efficient fine-tuning of large models. Unlike traditional parameter-efficient fine-tuning methods that operate within a large single subspace of the network weights, AdaMSS leverages subspace segmentation to obtain multiple smaller subspaces and adaptively reduces the number of trainable parameters during training, ultimately updating only those associated with a small subset of subspaces most relevant to the target downstream task. By using the lowest-rank representation, AdaMSS achieves more compact expressiveness and finer tuning of the model parameters. Theoretical analyses demonstrate that AdaMSS has better generalization guarantee than LoRA, PiSSA, and other single-subspace low-rank-based methods. Extensive experiments across image classification, natural language understanding, and natural language generation tasks show that AdaMSS achieves comparable performance to full fine-tuning and outperforms other parameter-efficient fine-tuning methods in most cases, all while requiring fewer trainable parameters. Notably, on the ViT-Large model, AdaMSS achieves 4.7\% higher average accuracy than LoRA across seven tasks, using just 15.4\% of the trainable parameters. On RoBERTa-Large, AdaMSS outperforms PiSSA by 7\% in average accuracy across six tasks while reducing the number of trainable parameters by approximately 94.4\%. These results demonstrate the effectiveness of AdaMSS in parameter-efficient fine-tuning.

Multi-agent language systems are often built as hand-designed workflows, where agents are assigned semantic roles and communication protocols are specified in advance. We propose NeuroMAS, a method that first treats a multi-agent language system as a trainable and scalable neural-network-like architecture with LLM agents as nodes and intermediate textual signals as edges. In NeuroMAS, agent nodes are role-free but structure-aware: the topology only determines how information can flow in general, while reinforcement learning training determines how nodes communicate, specialize, and coordinate. This formulation shifts multi-agent design from workflow engineering toward architecture design, where depth, width, connectivity, and growth protocol become scalable sources of capability. Further, we provide a theoretical perspective showing why such modular textual computation is more parameter-efficient when tasks admit hierarchical decompositions. Experiments show that NeuroMAS improves significantly over both inference-time and trained multi-agent baselines. We further find that organizational scaling is path-dependent: larger systems can be challenging to train from scratch, but become feasible when grown progressively from smaller trained systems. These results suggest that learned neural multi-agent systems are a promising scaling axis for LLMs.

Orthogonal parameter-efficient fine-tuning (PEFT) adapts pretrained weights through structure-preserving multiplicative transformations, but existing methods often conflate two distinct design choices: the subspace in which adaptation occurs and the transformation applied within that subspace. This paper introduces LOFT, a low-rank orthogonal fine-tuning framework that explicitly separates these two components. By viewing orthogonal adaptation as a multiplicative subspace rotation, LOFT provides a unified formulation that recovers representative orthogonal PEFT methods, including coordinate-, butterfly-, Householder-, and principal-subspace-based variants. More importantly, this perspective exposes support selection as a central design axis rather than a byproduct of a particular parameterization. We develop a first-order analysis showing that useful adaptation supports should be informed by the downstream training signal, motivating practical task-aware support selection strategies. Across language understanding, visual transfer, mathematical reasoning, and multilingual out-of-distribution adaptation, LOFT recovers principal-subspace orthogonal adaptation while gradient-informed supports improve the efficiency-performance trade-off under matched parameter, memory, and compute budgets. These results suggest that principled support selection is an important direction for improving orthogonal PEFT.

Machine learning - specifically deep learning - techniques have shown their capabilities in approximating dynamics from data, but a shortcoming of traditional deep learning is that there is little insight into the underlying mapping beyond its numerical output for a given input. This limits their utility in analysis beyond simple prediction. Simultaneously, a number of strategies exist which identify models based on a fixed dictionary of basis functions, but most either require some intuition or insight about the system, or are susceptible to overfitting or a lack of parsimony. Here we present a novel approach that combines the flexibility and accuracy of deep learning approaches with the utility of symbolic solutions: a deep neural network that generates a symbolic expression for the governing equations. We first describe the architecture for our model, then show the accuracy of our algorithm across a range of classical dynamical systems. The dynamics of quantities of interest are widely modeled A number of authors have approached system identificaas differential equations, often derived from first princi-tion by fitting coefficients of a linear combination of basis 3ples. However, this is not always possible, especially whenfunctions, dating at least back to Crutchfield and McNamara . The The set of basis functions typically includes nonlinear terms, identification of models from data has seen significant ad-for example terms which would arise in a Taylor series exvances with the advent of machine learning. While deeppansion about the origin of the system3-6 or a broader class neural networks have enabled sufficient accuracy in fore-of functions7. The coefficients of the basis functions are decasting dynamic data with unprecedented versatility, thetermined through comparison of the original data points with models they represent lack closed-form expressions thatpoints from computed solutions to the fitted models. Varican be conducive to interpretation and analysis.

Existing fine-tuning methods either tune all parameters of the pre-trained model (full fine-tuning), which is not efficient, or only tune the last linear layer (linear probing), which suffers a significant accuracy drop compared to the full fine-tuning. In this paper, we propose a new parameter-efficient fine-tuning method termed as SSF, representing that researchers only need to Scale and Shift the deep Features extracted by a pre-trained model to catch up with the performance of full finetuning. In this way, SSF also surprisingly outperforms other parameter-efficient fine-tuning approaches even with a smaller number of tunable parameters. Furthermore, different from some existing parameter-efficient fine-tuning methods (e.g., Adapter or VPT) that introduce the extra parameters and computational cost in the training and inference stages, SSF only adds learnable parameters during the training stage, and these additional parameters can be merged into the original pre-trained model weights via re-parameterization in the inference phase.

The code for our experiments is available at https://github.com/AndyShih12/HyperSPN. To examine the merits of HyperSPNs as discussed in Section 3, we construct a hand-crafted dataset to test the three types of models described in Figure 4: SPN-Large, SPN-Small, and HyperSPN. The hand-crafted dataset is procedurally generated with 256 binary variables and 10000 instances, broken into train/valid/test splits at 70/10/20%. The generation procedure is designed such that the correlation between variable i and j is dependent on the path length between leaves i and j of a complete binary tree over the 256 variables. The exact details can be found in our code.