English
Related papers

Related papers: Combatting Dimensional Collapse in LLM Pre-Trainin…

200 papers

Current trends in pre-training Large Language Models (LLMs) primarily focus on the scaling of model and dataset size. While the quality of pre-training data is considered an important factor for training powerful LLMs, it remains a nebulous…

Computation and Language · Computer Science 2025-07-04 Brando Miranda , Alycia Lee , Sudharsan Sundar , Allison Casasola , Rylan Schaeffer , Elyas Obbad , Sanmi Koyejo

A good feature representation is the key to image classification. In practice, image classifiers may be applied in scenarios different from what they have been trained on. This so-called domain shift leads to a significant performance drop…

Computer Vision and Pattern Recognition · Computer Science 2024-01-10 Zhize Wu , Changjiang Du , Le Zou , Ming Tan , Tong Xu , Fan Cheng , Fudong Nian , Thomas Weise

Federated Retrieval (FR) routes queries across multiple external knowledge sources, to mitigate hallucinations of LLMs, when necessary external knowledge is distributed. However, existing methods struggle to retrieve high-quality and…

Machine Learning · Computer Science 2025-10-15 Zhibang Yang , Xinke Jiang , Rihong Qiu , Ruiqing Li , Yihang Zhang , Yue Fang , Yongxin Xu , Hongxin Ding , Xu Chu , Junfeng Zhao , Yasha Wang

Large language models (LLMs) are increasingly used to automate feature engineering in tabular learning. Given task-specific information, LLMs can propose diverse feature transformation operations to enhance downstream model performance.…

Machine Learning · Computer Science 2026-01-30 Zhuoyan Li , Aditya Bansal , Jinzhao Li , Shishuang He , Zhuoran Lu , Mutian Zhang , Qin Liu , Yiwei Yang , Swati Jain , Ming Yin , Yunyao Li

Effective data selection is critical for efficient training of modern Large Language Models (LLMs). This paper introduces Influence Distillation, a novel, mathematically-justified framework for data selection that employs second-order…

Computation and Language · Computer Science 2025-05-27 Mahdi Nikdan , Vincent Cohen-Addad , Dan Alistarh , Vahab Mirrokni

Feature selection is an important tool to deal with high dimensional data. In unsupervised case, many popular algorithms aim at maintaining the structure of the original data. In this paper, we propose a simple and effective feature…

Machine Learning · Statistics 2020-04-06 Xiaoyun Li , Chengxi Wu , Ping Li

Recent efforts in fine-tuning language models often rely on automatic data selection, commonly using Nearest Neighbors retrieval from large datasets. However, we theoretically show that this approach tends to select redundant data, limiting…

Machine Learning · Computer Science 2025-02-11 Jonas Hübotter , Sascha Bongni , Ido Hakimi , Andreas Krause

Multimodal Sentiment Analysis (MSA) leverages heterogeneous modalities, such as language, vision, and audio, to enhance the understanding of human sentiment. While existing models often focus on extracting shared information across…

Machine Learning · Computer Science 2025-04-10 Pan Wang , Qiang Zhou , Yawen Wu , Tianlong Chen , Jingtong Hu

Federated Learning (FL) enables collaborative model training across decentralized clients without sharing private data. However, FL suffers from biased global models due to non-IID and long-tail data distributions. We propose…

Machine Learning · Computer Science 2026-01-08 Jingrui Zhang , Yimeng Xu , Shujie Li , Feng Liang , Haihan Duan , Yanjie Dong , Victor C. M. Leung , Xiping Hu

The rapid proliferation of large language models (LLMs) has created an unprecedented demand for fine-tuning models for specialized domains, such as medical science. While federated learning (FL) offers a decentralized and privacy-preserving…

Machine Learning · Computer Science 2025-06-25 Amir Faiyaz , Tara Salman

Large-scale Hierarchical Classification (HC) involves datasets consisting of thousands of classes and millions of training instances with high-dimensional features posing several big data challenges. Feature selection that aims to select…

Machine Learning · Computer Science 2017-06-07 Azad Naik , Huzefa Rangwala

Test-time adaptation paradigm provides flexibility towards domain shifts by performing immediate adaptation on unlabeled target data from the source model. Vision-Language Models (VLMs) leverage their generalization capabilities for diverse…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Jisu Han , Wonjun Hwang

Prompt engineering is essential for optimizing large language models (LLMs), yet the link between prompt structures and task performance remains underexplored. This work introduces an evolutionary approach that combines context-free grammar…

Computation and Language · Computer Science 2025-04-22 Gabriel Machado Santos , Rita Maria da Silva Julia , Marcelo Zanchetta do Nascimento

Distributed and federated learning are important tools for high-dimensional classification of large datasets. To reduce computational costs and overcome the curse of dimensionality, feature screening plays a pivotal role in eliminating…

Machine Learning · Statistics 2025-06-03 Qi Qin , Erbo Li , Xingxiang Li , Yifan Sun , Wu Wang , Chen Xu

This study investigates how to efficiently build a domain-specialized large language model (LLM) for statistics using the lightweight LLaMA-3.2-3B family as the foundation model (FM). We systematically compare three multi-stage training…

Computation and Language · Computer Science 2026-02-12 Jing-Yi Zeng , Guan-Hua Huang

Automatic data selection and curriculum design for training large language models is challenging, with only a few existing methods showing improvements over standard training. Furthermore, current schemes focus on domain-level selection,…

Computation and Language · Computer Science 2023-10-25 Simin Fan , Martin Jaggi

Gradient-based preference optimization methods for large language model (LLM) alignment suffer from preference collapse, converging to narrow behavioral modes while neglecting preference diversity. We introduce EvoPref, a multi-objective…

Neural and Evolutionary Computing · Computer Science 2026-05-12 Dongxin Guo , Jikun Wu , Siu Ming Yiu

Deploying Large Language Models (LLMs) on resource-constrained (or weak) devices presents significant challenges due to limited resources and heterogeneous data distribution. To address the data concern, it is necessary to fine-tune LLMs…

Machine Learning · Computer Science 2025-01-07 Zhiwei Yao , Yang Xu , Hongli Xu , Yunming Liao , Zuan Xie

Extensive efforts have been made to boost the performance in the domain of language models by introducing various attention-based transformers. However, the inclusion of linear layers with large dimensions contributes to significant…

Machine Learning · Computer Science 2024-11-19 Priyansh Bhatnagar , Linfeng Wen , Mingu Kang

Non-uniform structured network pruning methods can effectively reduce Large Language Model (LLM) size by eliminating redundant channels or layers, offering lower performance degradation than uniform strategies. However, existing non-uniform…

Machine Learning · Computer Science 2025-08-07 Zuxin Ma , Yunhe Cui , Yongbin Qin
‹ Prev 1 8 9 10 Next ›