English
Related papers

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

200 papers

Fine-tuning large language models (LLMs) using diverse datasets is crucial for enhancing their overall performance across various domains. In practical scenarios, existing methods based on modeling the mixture proportions of data…

Computation and Language · Computer Science 2025-10-31 Zhenqing Ling , Daoyuan Chen , Liuyi Yao , Qianli Shen , Yaliang Li , Ying Shen

Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding but suffer from prohibitive quadratic computational complexity and memory overhead during inference. Current caching techniques accelerate…

Computation and Language · Computer Science 2025-11-06 Yuerong Song , Xiaoran Liu , Ruixiao Li , Zhigeng Liu , Zengfeng Huang , Qipeng Guo , Ziwei He , Xipeng Qiu

Recent progress in large language models (LLMs) has leveraged their in-context learning (ICL) abilities to enable quick adaptation to unseen biomedical NLP tasks. By incorporating only a few input-output examples into prompts, LLMs can…

Computation and Language · Computer Science 2025-08-12 Jun Wang , Zaifu Zhan , Qixin Zhang , Mingquan Lin , Meijia Song , Rui Zhang

Label-scarce visual classification under decentralized and heterogeneous data is a fundamental challenge in pattern recognition, especially when sites exhibit partially overlapping class sets. While self-supervised federated learning (SSFL)…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Mingkun Tan , Xilu Wang , Michael Kloster , Tim W. Nattkemper

Large language models (LLMs) deliver impressive results but face challenges from increasing model sizes and computational costs. Structured pruning reduces model size and speeds up inference but often causes uneven degradation across…

Computation and Language · Computer Science 2025-05-28 Hexuan Deng , Wenxiang Jiao , Xuebo Liu , Jing Li , Min Zhang , Zhaopeng Tu

Source-Free Cross-Domain Few-Shot Learning (SF-CDFSL) focuses on fine-tuning with limited training data from target domains (e.g., medical or satellite images), where Vision-Language Models (VLMs) such as CLIP and SigLIP have shown…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Zhenyu Zhang , Yixiong Zou , Yuhua Li , Ruixuan Li , Guangyao Chen

While recent advances in preference learning have enhanced alignment in human feedback, mathematical reasoning remains a persistent challenge. We investigate how data diversification strategies in preference optimization can improve the…

Artificial Intelligence · Computer Science 2025-07-04 Berkan Dokmeci , Qingyang Wu , Ben Athiwaratkun , Ce Zhang , Shuaiwen Leon Song , James Zou

We explore the impact of training with more diverse datasets, characterized by the number of unique samples, on the performance of self-supervised learning (SSL) under a fixed computational budget. Our findings consistently demonstrate that…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Hasan Abed Al Kader Hammoud , Tuhin Das , Fabio Pizzati , Philip Torr , Adel Bibi , Bernard Ghanem

Diversity optimization seeks to discover a set of solutions that elicit diverse features. Prior work has proposed Novelty Search (NS), which, given a current set of solutions, seeks to expand the set by finding points in areas of low…

Machine Learning · Computer Science 2024-05-31 David H. Lee , Anishalakshmi V. Palaparthi , Matthew C. Fontaine , Bryon Tjanaka , Stefanos Nikolaidis

The rapid development of Large Language Models (LLMs) creates new opportunities for recommender systems, especially by exploiting the side information (e.g., descriptions and analyses of items) generated by these models. However, aligning…

Information Retrieval · Computer Science 2025-04-14 Guixian Zhang , Guan Yuan , Debo Cheng , Lin Liu , Jiuyong Li , Shichao Zhang

Large language models (LLMs) have demonstrated remarkable capabilities, but their massive scale poses significant challenges for practical deployment. Structured pruning offers a promising solution by removing entire dimensions or layers,…

Machine Learning · Computer Science 2026-05-27 Jimyung Hong , Jaehyung Kim

When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on…

Computation and Language · Computer Science 2025-05-26 Xiang Liu , Zhaoxiang Liu , Peng Wang , Kohou Wang , Huan Hu , Kai Wang , Shiguo Lian

Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation, leveraging parallel decoding and bidirectional attention to achieve superior global coherence compared to autoregressive models. While…

Machine Learning · Computer Science 2026-01-28 Zhongyu Xiao , Zhiwei Hao , Jianyuan Guo , Yong Luo , Jia Liu , Jie Xu , Han Hu

In recent years, the use of large language models (LLMs) for text classification has attracted widespread attention. Despite this, the classification accuracy of LLMs has not yet universally surpassed that of smaller models. LLMs can…

Computation and Language · Computer Science 2024-12-11 Min Zeng , Caiquan Liu , Shiqi Zhang , Li Xie , Chen Sang , Xiaoxin Chen

Computational virtual high-throughput screening (VHTS) with density functional theory (DFT) and machine-learning (ML)-acceleration is essential in rapid materials discovery. By necessity, efficient DFT-based workflows are carried out with a…

Materials Science · Physics 2021-06-25 Chenru Duan , Shuxin Chen , Michael G. Taylor , Fang Liu , Heather J. Kulik

Large language model (LLM) alignment is typically achieved through learning from human preference comparisons, making the quality of preference data critical to its success. Existing studies often pre-process raw training datasets to…

Machine Learning · Computer Science 2026-03-17 Zizhuo Zhang , Qizhou Wang , Shanshan Ye , Jianing Zhu , Jiangchao Yao , Bo Han , Masashi Sugiyama

Large Language Models (LLMs) have achieved significant success across various NLP tasks. However, their massive computational costs limit their widespread use, particularly in real-time applications. Structured pruning offers an effective…

Machine Learning · Computer Science 2025-03-06 Shengkun Tang , Oliver Sieberling , Eldar Kurtic , Zhiqiang Shen , Dan Alistarh

Self-supervised learning (SSL) approaches have achieved great success when the amount of labeled data is limited. Within SSL, models learn robust feature representations by solving pretext tasks. One such pretext task is contrastive…

Computer Vision and Pattern Recognition · Computer Science 2024-02-28 Jamshid Hassanpour , Vinkle Srivastav , Didier Mutter , Nicolas Padoy

Large language models (LLMs) offer a scalable mechanism to elicit domain-informed prior information for high-dimensional variable selection. However, existing methods such as LLM-Lasso are sensitive to weight quality, with performance…

Machine Learning · Statistics 2026-05-25 Caleb Skinner , Yihan Guo , Meng Li

While the SLIM approach obtained high ranking-accuracy in many experiments in the literature, it is also known for its high computational cost of learning its parameters from data. For this reason, we focus in this paper on variants of…

Information Retrieval · Computer Science 2019-05-01 Harald Steck