English
Related papers

Related papers: AlphaDecay: Module-wise Weight Decay for Heavy-Tai…

200 papers

Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to self-adapt by…

Machine Learning · Computer Science 2025-09-19 Adam Zweiger , Jyothish Pari , Han Guo , Ekin Akyürek , Yoon Kim , Pulkit Agrawal

Deep learning based models are used regularly in every applications nowadays. Generally we train a single model on a single task. However, we can train multiple tasks on a single model under multi-task learning settings. This provides us…

Machine Learning · Computer Science 2023-03-14 Aminul Huq , Mst Tasnim Pervin

During the finetuning stage of text generation tasks, standard cross-entropy loss treats all tokens equally. This can lead models to overemphasize high-frequency, low-information tokens, neglecting lower-frequency tokens crucial for…

Computation and Language · Computer Science 2025-06-10 Jintian Shao

Multi-task learning (MTL) trains deep neural networks to optimize several objectives simultaneously using a shared backbone, which leads to reduced computational costs, improved data efficiency, and enhanced performance through cross-task…

Machine Learning · Computer Science 2025-09-30 Hoang Phan , Lam Tran , Quyen Tran , Ngoc N. Tran , Tuan Truong , Qi Lei , Nhat Ho , Dinh Phung , Trung Le

Training Large Language Models (LLMs) at ultra-low precision is critically impeded by instability rooted in the conflict between discrete quantization constraints and the intrinsic heavy-tailed spectral nature of linguistic data. By…

Machine Learning · Computer Science 2026-02-03 Junlin Huang , Wenyi Fang , Zhenheng Tang , Yuxin Wang , Xueze Kang , Yang Zheng , Bo Li , Xiaowen Chu

Anomaly detection is crucial in industrial applications for identifying rare and unseen patterns to ensure system reliability. Traditional models, trained on a single class of normal data, struggle with real-world distributions where normal…

Machine Learning · Statistics 2026-01-07 Jungi Lee , Jungkwon Kim , Chi Zhang , Sangmin Kim , Kwangsun Yoo , Seok-Joo Byun

Recent work has shown that optimizing the Learning Rate (LR) schedule can be a very accurate and efficient way to train deep neural networks. We observe that the rate of change (ROC) of LR has correlation with the training process, but how…

Machine Learning · Computer Science 2022-03-23 Tao Zhang , Wei Li

Large Language Models (LLMs) possess outstanding capabilities in addressing various natural language processing (NLP) tasks. However, the sheer size of these models poses challenges in terms of storage, training and inference due to the…

Computation and Language · Computer Science 2025-04-18 Shuzhou Yuan , Ercong Nie , Bolei Ma , Michael Färber

Sparse autoencoders (SAEs) are widely used to extract human-interpretable features from neural network activations, but their learned features can vary substantially across random seeds and training choices. To improve stability, we studied…

Machine Learning · Statistics 2026-03-05 Piotr Jedryszek , Oliver M. Crook

Serving many task-specialized LLM variants is often limited by the large size of fine-tuned checkpoints and the resulting cold-start latency. Since fine-tuned weights differ from their base model by relatively small structured residuals, a…

Machine Learning · Computer Science 2025-12-24 Stefan Kuyumdzhiev , Radostin Cholakov

Conventional de-noising methods rely on the assumption that all samples are independent and identically distributed, so the resultant classifier, though disturbed by noise, can still easily identify the noises as the outliers of training…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Xuanyu Yi , Kaihua Tang , Xian-Sheng Hua , Joo-Hwee Lim , Hanwang Zhang

Large language models achieve exceptional performance on various downstream tasks through supervised fine-tuning. However, the diversity of downstream tasks and practical requirements makes deploying multiple full-parameter fine-tuned…

Machine Learning · Computer Science 2024-10-14 Yanfeng Jiang , Zelan Yang , Bohua Chen , Shen Li , Yong Li , Tao Li

In the field of large language model (LLM) compression, singular value decomposition (SVD) is a widely studied and adopted low-rank decomposition technique. Since SVD operates exclusively on linear modules, and these modules in LLMs are…

Machine Learning · Computer Science 2025-10-23 Lin Xv , Jingsheng Gao , Xian Gao , Ting Liu , Yuzhuo Fu

The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing interpretability methods, particularly those based on activations, often require or assume…

Machine Learning · Computer Science 2026-04-22 Ziqian Zhong , Aditi Raghunathan

We explore efficient strategies to fine-tune decoder-only Large Language Models (LLMs) for downstream text classification under resource constraints. Two approaches are investigated: (1) attaching a classification head to a pretrained…

Computation and Language · Computer Science 2026-05-26 Amirhossein Yousefiramandi , Ciaran Cooney

Federated Multi-Task Learning (FMTL) enables multiple clients performing heterogeneous tasks without exchanging their local data, offering broad potential for privacy preserving multi-task collaboration. However, most existing methods focus…

Machine Learning · Computer Science 2025-06-02 Yipan Wei , Yuchen Zou , Yapeng Li , Bo Du

Large language models (LLMs) achieve strong performance across diverse tasks but suffer from high inference latency due to their autoregressive generation. Speculative Decoding (SPD) mitigates this issue by verifying candidate tokens in…

Computation and Language · Computer Science 2026-04-30 Jinze Li , Yixing Xu , Guanchen Li , Shuo Yang , Jinfeng Xu , Xuanwu Yin , Dong Li , Edith C. H. Ngai , Emad Barsoum

Parameter-efficient fine-tuning techniques like Low-Rank Adaptation (LoRA) have revolutionized the adaptation of large language models (LLMs) to diverse tasks. Recent efforts have explored mixtures of LoRA modules for multi-task settings.…

Computation and Language · Computer Science 2024-08-06 Lin Ning , Harsh Lara , Meiqi Guo , Abhinav Rastogi

Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase, thereby leading to the deterioration of the tail performance. Existing solutions usually address this issue via…

Machine Learning · Computer Science 2023-01-26 Haiyang Yu , Ningyu Zhang , Shumin Deng , Zonggang Yuan , Yantao Jia , Huajun Chen

Deep neural networks are learning models with a very high capacity and therefore prone to over-fitting. Many regularization techniques such as Dropout, DropConnect, and weight decay all attempt to solve the problem of over-fitting by…

Machine Learning · Computer Science 2016-12-06 Armen Aghajanyan
‹ Prev 1 3 4 5 6 7 10 Next ›