English
Related papers

Related papers: DynamixSFT: Dynamic Mixture Optimization of Instru…

200 papers

Benefiting from prompt tuning, recent years have witnessed the promising performance of pre-trained vision-language models, e.g., CLIP, on versatile downstream tasks. In this paper, we focus on a particular setting of learning adaptive…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Chun-Mei Feng , Kai Yu , Yong Liu , Salman Khan , Wangmeng Zuo

Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization. While data augmentation is widely used to enhance…

Machine Learning · Computer Science 2025-05-13 Suorong Yang , Peng Ye , Furao Shen , Dongzhan Zhou

Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages.…

Computation and Language · Computer Science 2024-07-03 Sathish Reddy Indurthi , Wenxuan Zhou , Shamil Chollampatt , Ravi Agrawal , Kaiqiang Song , Lingxiao Zhao , Chenguang Zhu

Aligning features from different modalities, is one of the most fundamental challenges for cross-modal tasks. Although pre-trained vision-language models can achieve a general alignment between image and text, they often require…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Ziqi Jiang , Yanghao Wang , Long Chen

Reinforcement finetuning (RFT) has shown great potential for enhancing the mathematical reasoning capabilities of large language models (LLMs), but it is often sample- and compute-inefficient, requiring extensive training. In this work, we…

Machine Learning · Computer Science 2026-02-03 Taiwei Shi , Yiyang Wu , Linxin Song , Tianyi Zhou , Jieyu Zhao

Instruction tuning has emerged to enhance the capabilities of large language models (LLMs) to comprehend instructions and generate appropriate responses. Existing methods either manually annotate or employ LLM (e.g., GPT-series) to generate…

Computation and Language · Computer Science 2023-10-27 Da Yin , Xiao Liu , Fan Yin , Ming Zhong , Hritik Bansal , Jiawei Han , Kai-Wei Chang

Learning from Demonstration (LfD) approaches empower end-users to teach robots novel tasks via demonstrations of the desired behaviors, democratizing access to robotics. A key challenge in LfD research is that users tend to provide…

Machine Learning · Computer Science 2022-02-16 Sravan Jayanthi , Letian Chen , Matthew Gombolay

As Large Language Models (LLMs) are increasingly applied across various tasks, instruction tuning has emerged as a critical method for enhancing model performance. However, current data management strategies face substantial challenges in…

Computation and Language · Computer Science 2025-04-15 Yangning Li , Zihua Lan , Lv Qingsong , Yinghui Li , Hai-Tao Zheng

Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains. In this study, we introduce a novel mixed-sample data augmentation method called RandoMix. RandoMix is…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Xiaoliang Liu , Furao Shen , Jian Zhao , Changhai Nie

Instruction tuning improves the reasoning abilities of large language models (LLMs), with data quality and scalability being the crucial factors. Most instruction tuning data come from human crowd-sourcing or GPT-4 distillation. We propose…

Computation and Language · Computer Science 2024-05-24 Xiang Yue , Tuney Zheng , Ge Zhang , Wenhu Chen

Optimizing data mixtures is essential for unlocking the full potential of large language models (LLMs), yet identifying the optimal composition remains computationally prohibitive due to reliance on heuristic trials or expensive proxy…

Machine Learning · Computer Science 2026-01-27 Jiapeng Wang , Changxin Tian , Kunlong Chen , Ziqi Liu , Jiaxin Mao , Wayne Xin Zhao , Zhiqiang Zhang , Jun Zhou

Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimodal training recipes tune mixtures along a single dimension,…

Machine Learning · Computer Science 2026-04-17 Bingbing Wen , Sirajul Salekin , Feiyang Kang , Bill Howe , Lucy Lu Wang , Javier Movellan , Manjot Bilkhu

This paper studies the training-testing discrepancy (a.k.a. exposure bias) problem for improving the diffusion models. During training, the input of a prediction network at one training timestep is the corresponding ground-truth noisy data…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Hui Li , Jiayue Lyu , Fu-Yun Wang , Kaihui Cheng , Siyu Zhu , Jingdong Wang

Finetuning on domain-specific data is a well-established method for enhancing LLM performance on downstream tasks. Training on each dataset produces a new set of model weights, resulting in a multitude of checkpoints saved in-house or on…

Machine Learning · Computer Science 2026-03-12 Sofia Maria Lo Cicero Vaina , Artem Chumachenko , Max Ryabinin

Increasingly large imitation learning datasets are being collected with the goal of training foundation models for robotics. However, despite the fact that data selection has been of utmost importance in vision and natural language…

Robotics · Computer Science 2025-02-24 Joey Hejna , Chethan Bhateja , Yichen Jiang , Karl Pertsch , Dorsa Sadigh

Instruction tuning is a standard technique employed to align large language models to end tasks and user preferences after the initial pretraining phase. Recent research indicates the critical role of data engineering in instruction tuning…

Computation and Language · Computer Science 2024-04-17 Wei Liu , Weihao Zeng , Keqing He , Yong Jiang , Junxian He

Determining the optimal data mixture for large language model training remains a challenging problem with an outsized impact on performance. In practice, language model developers continue to rely on heuristic exploration since no…

Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models, but it often degrades pretrained capabilities such as reasoning and general-domain performance. We argue this forgetting arises because fine-tuning…

Computation and Language · Computer Science 2026-05-22 Jiarui Liu , Lechen Zhang , Yongjin Yang , Yinghui He , Yingheng Wang , Weihao Xuan , Zhijing Jin , Mona Diab

Supervised fine-tuning (SFT) data selection is commonly formulated as instance ranking: score each example and retain a top-$k$ subset. However, effective SFT training subsets are often produced through ordered curation recipes, where…

Machine Learning · Computer Science 2026-05-14 Haodong Wu , Jiahao Zhang , Lijie Hu , Yongqi Zhang

Finetuning large language models with a variety of instruction-response pairs has enhanced their capability to understand and follow instructions. Current instruction tuning primarily relies on teacher models or human intervention to…

Computation and Language · Computer Science 2025-06-06 Ming Li , Pei Chen , Chenguang Wang , Hongyu Zhao , Yijun Liang , Yupeng Hou , Fuxiao Liu , Tianyi Zhou