相关论文: Orthogonal Subspace Projection for Continual Machi…

Video super-resolution (VSR) aims to reconstruct a sequence of high-resolution (HR) images from their corresponding low-resolution (LR) versions. Traditionally, solving a VSR problem has been based on iterative algorithms that can exploit…

Neural networks are achieving state of the art and sometimes super-human performance on learning tasks across a variety of domains. Whenever these problems require learning in a continual or sequential manner, however, neural networks…

Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters.…

Although pre-trained Vision-Language-Action (VLA) models exhibit impressive generalization in robotic manipulation, post-training remains crucial to ensure reliable performance during deployment. However, standard offline Supervised…

Scaling multi-task low-rank adaptation (LoRA) to a large number of tasks induces catastrophic performance degradation, such as an accuracy drop from 88.2% to 2.0% on DOTA when scaling from 5 to 15 tasks. This failure is due to parameter and…

Multimodal recommendation systems (MRS) jointly model user-item interaction graphs and rich item content, but this tight coupling makes user data difficult to remove once learned. Approximate machine unlearning offers an efficient…

The massive scale of pretrained models has made efficient compression essential for practical deployment. Low-rank decomposition based on the singular value decomposition (SVD) provides a principled approach for model reduction, but its…

Scaling critic capacity is a promising direction for improving off-policy reinforcement learning (RL). However, recent work shows that larger critics are prone to overfitting and instability in replay-based bootstrapped training. In this…

Unconstrained fine-tuning of flow-matching Vision-Language-Action (VLA) models drives dense parameter overwrites, degrading pre-trained capabilities. We present Conservative Supervised Fine-Tuning (ConSFT), an optimization objective that…

Machine unlearning aims to enable models to forget specific data instances when receiving deletion requests. Current research centres on efficient unlearning to erase the influence of data from the model and neglects the subsequent impacts…

Multimodal recommendation enhances accuracy by leveraging visual and textual signals, and its success largely depends on learning high-quality cross-modal representations. Recent advances in Large Vision-Language Models (LVLMs) offer…

Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge…

Parameter-efficient fine-tuning methods, such as LoRA, reduces the number of trainable parameters. However, they often suffer from scalability issues and differences between their learning pattern and full fine-tuning. To overcome these…

Decentralized federated learning (DFL), a serverless variant of federated learning, poses unique challenges for parameter-efficient fine-tuning due to the factorized structure of low-rank adaptation (LoRA). Unlike linear parameters,…

LoRA-based large model parameter-efficient fine-tuning (PEFT) methods use low-rank de- composition to approximate updates to model parameters. However, compared to full- parameter fine-tuning, low-rank updates often lead to a performance…

Continual learning (CL) requires models to continuously adapt to new tasks without forgetting past knowledge. In this work, we propose \underline{P}roactive \underline{L}ow-rank \underline{A}llocatio\underline{N} (PLAN), a framework that…

Low-Rank Adaptation (LoRA) is a parameter-efficient technique for rapidly fine-tuning foundation models. In standard LoRA training dynamics, models tend to quickly converge to a local optimum near the initialization. However, this local…

In this paper, we present a predictor-corrector strategy for constructing rank-adaptive dynamical low-rank approximations (DLRAs) of matrix-valued ODE systems. The strategy is a compromise between (i) low-rank step-truncation approaches…

Training large models ranging from millions to billions of parameters is highly resource-intensive, requiring significant time, compute, and memory. It is observed that most of the learning (higher change in weights) takes place in the…

Low-Rank Adaptation (LoRA) is one of the most widely used techniques for fine-tuning large language models (LLMs). By introducing a small number of trainable low-rank weight matrices, LoRA substantially reduces the number of parameters that…