相关论文: GradOT: Training-free Gradient-preserving Offsite-…

Large Language Models (LLMs) based on the pre-trained fine-tuning paradigm have become pivotal in solving natural language processing tasks, consistently achieving state-of-the-art performance. Nevertheless, the theoretical understanding of…

Large Language Models (LLMs) are reshaping the research landscape in artificial intelligence, particularly as model parameters scale up significantly, unlocking remarkable capabilities across various domains. Nevertheless, the scalability…

In this paper, we propose objective-function-free (OFF) variants of the proximal Newton method for nonconvex composite optimization problems and the regularized Newton method for unconstrained optimization problems, respectively, using…

With the availability of large pre-trained models, a modern workflow for building real-world machine learning solutions is to fine-tune such models on a downstream task with a relatively small domain-specific dataset. In such applications,…

Large Language Models (LLMs) have become indispensable in numerous real-world applications. However, fine-tuning these models at scale, especially in federated settings where data privacy and communication efficiency are critical, presents…

Unsupervised Outlier Detection (UOD) is a critical task in data mining and machine learning, aiming to identify instances that significantly deviate from the majority. Without any label, deep UOD methods struggle with the misalignment…

Training large language models (LLMs) is highly memory-intensive, as training must store not only weights and optimizer states but also intermediate activations for backpropagation. While existing memory-efficient methods largely focus on…

Latent space optimization (LSO) is a powerful method for designing discrete, high-dimensional biological sequences that maximize expensive black-box functions, such as wet lab experiments. This is accomplished by learning a latent space…

Large Language Models (LLMs) are changing the coding paradigm, known as vibe coding, yet synthesizing algorithmically sophisticated and robust code still remains a critical challenge. Incentivizing the deep reasoning capabilities of LLMs is…

A major challenge in training large-scale machine learning models is configuring the training process to maximize model performance, i.e., finding the best training setup from a vast design space. In this work, we unlock a gradient-based…

The increasing size and complexity of Large Language Models (LLMs) pose challenges for their deployment on personal computers and mobile devices. Aggressive post-training model compression is necessary to reduce the models' size, but it…

Mastering a skill generally relies on both hands-on experience from doers and insightful, high-level guidance by mentors. Will this strategy also work well for solving complex non-convex optimization problems? Here, a common gradient-based…

Contrastive vision-language models like CLIP exhibit remarkable zero-shot generalization. However, prompt tuning remains highly sensitive to label noise, as mislabeled samples generate disproportionately large gradients that can overwhelm…

We study the Unbalanced Optimal Transport (UOT) between two measures of possibly different masses with at most $n$ components, where the marginal constraints of standard Optimal Transport (OT) are relaxed via Kullback-Leibler divergence…

Due to the substantial computational cost, training state-of-the-art deep neural networks for large-scale datasets often requires distributed training using multiple computation workers. However, by nature, workers need to frequently…

Large Language Models (LLMs) have transformed natural language processing tasks successfully. Yet, their large size and high computational needs pose challenges for practical use, especially in resource-limited settings. Model compression…

Large language models often require fine-tuning to better align their behavior with user intent at deployment. Existing approaches are commonly divided into online and offline paradigms. Online methods, such as RL-based alignment, can…

The reusability of state-of-the-art Pre-trained Language Models (PLMs) is often limited by their generalization problem, where their performance drastically decreases when evaluated on examples that differ from the training dataset, known…

Continual learning in multimodal large language models (MLLMs) aims to sequentially acquire knowledge while mitigating catastrophic forgetting, yet existing methods face inherent limitations: architecture-based approaches incur additional…

Large Language Models are growing in size, and we expect them to continue to do so, as larger models train quicker. However, this increase in size will severely impact inference costs. Therefore model compression is important, to retain the…