English
Related papers

Related papers: Grow, Don't Overwrite: Fine-tuning Without Forgett…

200 papers

Optimizers play an important role in both pretraining and finetuning stages when training large language models (LLMs). In this paper, we present an observation that full finetuning with the same optimizer as in pretraining achieves a…

Machine Learning · Computer Science 2026-05-08 Yuxing Liu , Jianyu Wang , Tong Zhang

Catastrophic forgetting remains a major challenge when fine-tuning large language models (LLMs) on narrow, task-specific data, often degrading their general knowledge and reasoning abilities. We propose SA-SFT, a lightweight…

Computation and Language · Computer Science 2026-02-25 Yutao Sun , Mingshuai Chen , Tiancheng Zhao , Phillip Miao , Zilun Zhang , Haozhan Shen , Ruizhe Zhu , Jianwei Yin

Large language models (LLMs) still struggle across tasks outside of high-resource languages. In this work, we investigate cross-lingual transfer to lower-resource languages where task-specific post-training data is scarce. Building on prior…

Computation and Language · Computer Science 2025-10-09 Lucas Bandarkar , Nanyun Peng

Post-training algorithms such as Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT) are widely used to adapt (multimodal) large language models to downstream tasks. While effective at task adaptation, their impact on retaining…

Computation and Language · Computer Science 2026-03-06 Zhihao Zhang , Qiaole Dong , Qi Zhang , Jun Zhao , Enyu Zhou , Zhiheng Xi , Senjie Jin , Xiaoran Fan , Yuhao Zhou , Mingqi Wu , Yanwei Fu , Tao Ji , Tao Gui , Xuanjing Huang , Kai Chen

Class-incremental continual learning is a core step towards developing artificial intelligence systems that can continuously adapt to changes in the environment by learning new concepts without forgetting those previously learned. This is…

Machine Learning · Computer Science 2023-07-07 Evelyn Chee , Mong Li Lee , Wynne Hsu

Continual pre-training has been urgent for adapting a pre-trained model to a multitude of domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is expected to demonstrate not only greater capacity when…

Computation and Language · Computer Science 2023-10-23 Gangwei Jiang , Caigao Jiang , Siqiao Xue , James Y. Zhang , Jun Zhou , Defu Lian , Ying Wei

To reduce model size during post-training, compression methods, including knowledge distillation, low-rank approximation, and pruning, are often applied after fine-tuning the model. However, sequential fine-tuning and compression sacrifices…

Machine Learning · Computer Science 2025-05-29 Xiangyu Chen , Jing Liu , Ye Wang , Matthew Brand , Pu , Wang , Toshiaki Koike-Akino

Large language models (LLMs) with one or more fine-tuning phases have become a necessary step to unlock various capabilities, enabling LLMs to follow natural language instructions or align with human preferences. However, it carries the…

Computation and Language · Computer Science 2024-04-30 Tingfeng Hui , Zhenyu Zhang , Shuohuan Wang , Weiran Xu , Yu Sun , Hua Wu

Reasoning is a core capability of large language models, yet how multi-step reasoning is learned and executed remains unclear. We study this question in a controlled cellular-automata (1dCA) framework that excludes memorisation by using…

During the pretraining phase, large language models (LLMs) acquire vast amounts of knowledge from extensive text corpora. Nevertheless, in later stages such as fine-tuning and inference, the model may encounter knowledge not covered in the…

Computation and Language · Computer Science 2024-10-10 Bozhou Li , Hao Liang , Yang Li , Fangcheng Fu , Hongzhi Yin , Conghui He , Wentao Zhang

Reusing pretrained base models for further pretraining, such as continual pretraining or model growth, is promising at reducing the cost of training language models from scratch. However, the effectiveness remains unclear, especially when…

Computation and Language · Computer Science 2026-02-04 Seng Pei Liew , Takuya Kato

Generalist robot policies, trained on large and diverse datasets, have demonstrated the ability to generalize across a wide spectrum of behaviors, enabling a single policy to act in varied real-world environments. However, they still fall…

Robotics · Computer Science 2026-03-03 Yajat Yadav , Zhiyuan Zhou , Andrew Wagenmaker , Karl Pertsch , Sergey Levine

Multimodal continual instruction tuning enables multimodal large language models to sequentially adapt to new tasks while building upon previously acquired knowledge. However, this continual learning paradigm faces the significant challenge…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Songze Li , Mingyu Gao , Tonghua Su , Xu-Yao Zhang , Zhongjie Wang

Effective decision-making in the real world depends on memory that is both stable and adaptive: environments change over time, and agents must retain relevant information over long horizons while also updating or overwriting outdated…

Machine Learning · Computer Science 2026-01-22 Oleg Shchendrigin , Egor Cherepanov , Alexey K. Kovalev , Aleksandr I. Panov

Adapting pre-trained foundation models for various downstream tasks has been prevalent in artificial intelligence. Due to the vast number of tasks and high costs, adjusting all parameters becomes unfeasible. To mitigate this, several…

Computer Vision and Pattern Recognition · Computer Science 2025-02-07 Chongjie Si , Xuehui Wang , Xue Yang , Zhengqin Xu , Qingyun Li , Jifeng Dai , Yu Qiao , Xiaokang Yang , Wei Shen

We explore a method for improving the performance of large language models through self-reflection and reinforcement learning. By incentivizing the model to generate better self-reflections when it answers incorrectly, we demonstrate that a…

Computation and Language · Computer Science 2025-06-02 Shelly Bensal , Umar Jamil , Christopher Bryant , Melisa Russak , Kiran Kamble , Dmytro Mozolevskyi , Muayad Ali , Waseem AlShikh

As a dominant paradigm, fine-tuning a pre-trained model on the target data is widely used in many deep learning applications, especially for small data sets. However, recent studies have empirically shown that training from scratch has the…

Computer Vision and Pattern Recognition · Computer Science 2022-05-27 Ziquan Liu , Yi Xu , Yuanhong Xu , Qi Qian , Hao Li , Xiangyang Ji , Antoni Chan , Rong Jin

A key stepping stone in the development of an artificial general intelligence (a machine that can perform any task), is the production of agents that can perform multiple tasks at once instead of just one. Unfortunately, canonical methods…

Neural and Evolutionary Computing · Computer Science 2019-04-08 Joseph Early

Fine-tuning pre-trained models for downstream tasks is a widely adopted technique known for its adaptability and reliability across various domains. Despite its conceptual simplicity, fine-tuning entails several troublesome engineering…

Artificial Intelligence · Computer Science 2024-12-30 Chaeyun Jang , Hyungi Lee , Jungtaek Kim , Juho Lee

The lifelong learning paradigm in machine learning is an attractive alternative to the more prominent isolated learning scheme not only due to its resemblance to biological learning but also its potential to reduce energy waste by obviating…

Machine Learning · Computer Science 2023-08-30 Sanket Vaibhav Mehta , Darshan Patil , Sarath Chandar , Emma Strubell
‹ Prev 1 8 9 10 Next ›