English
Related papers

Related papers: Tunable MAGMAX: Preference-Aware Model Merging for…

200 papers

In this paper, we propose a continual learning (CL) technique that is beneficial to sequential task learners by improving their retained accuracy and reducing catastrophic forgetting. The principal target of our approach is the automatic…

Machine Learning · Computer Science 2021-01-19 Ammar Shaker , Shujian Yu , Francesco Alesiani

Model Predictive Control (MPC) provides interpretable, tunable locomotion controllers grounded in physical models, but its robustness depends on frequent replanning and is limited by model mismatch and real-time computational constraints.…

Robotics · Computer Science 2025-10-15 Se Hwan Jeon , Ho Jae Lee , Seungwoo Hong , Sangbae Kim

Context-aware machine translation (MT) leverages document-level information, yet it does not consistently outperform sentence-level MT, as contextual signals are unevenly beneficial across sentences. Existing training objectives do not…

Computation and Language · Computer Science 2026-03-27 Ying Li , Xinglin Lyu , Junhui Li , Jinlong Yang , Hengchao Shang , Min Zhang , Shimin Tao , Daimeng Wei

Curriculum learning (CL) is a training strategy that trains a machine learning model from easier data to harder data, which imitates the meaningful learning order in human curricula. As an easy-to-use plug-in, the CL strategy has…

Machine Learning · Computer Science 2021-03-26 Xin Wang , Yudong Chen , Wenwu Zhu

Multi-task model merging aims to consolidate knowledge from multiple fine-tuned task-specific experts into a unified model while minimizing performance degradation. Existing methods primarily approach this by minimizing differences between…

Machine Learning · Computer Science 2025-10-28 Wenju Sun , Qingyong Li , Wen Wang , Yang Liu , Yangli-ao Geng , Boyang Li

Continual Model Merging (CMM) enables rapid customization of foundation models by sequentially incorporating task-adapted models without repeated retraining. However, existing merging rules usually update the deployed model through fixed…

Machine Learning · Computer Science 2026-05-26 Lihong Lin , Haidong Kang

Efficiently merging several models fine-tuned for different tasks, but stemming from the same pretrained base model, is of great practical interest. Despite extensive prior work, most evaluations of model merging in computer vision are…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Pau de Jorge , César Roberto de Souza , Björn Michele , Mert Bülent Sarıyıldız , Philippe Weinzaepfel , Florent Perronnin , Diane Larlus , Yannis Kalantidis

Large Language Models (LLMs) have been adopted and deployed worldwide for a broad variety of applications. However, ensuring their safe use remains a significant challenge. Preference training and safety measures often overfit to harms…

Computation and Language · Computer Science 2024-10-15 Aakanksha , Arash Ahmadian , Seraphina Goldfarb-Tarrant , Beyza Ermis , Marzieh Fadaee , Sara Hooker

A few recent studies have demonstrated that leveraging centrally pre-trained models can offer advantageous initializations for federated learning (FL). However, existing pre-training methods do not generalize well when faced with an…

Machine Learning · Computer Science 2024-12-12 Yun-Wei Chu , Dong-Jun Han , Seyyedali Hosseinalipour , Christopher G. Brinton

Combining multiple machine learning models has long been a technique for enhancing performance, particularly in distributed settings. Traditional approaches, such as model ensembles, work well, but are expensive in terms of memory and…

Machine Learning · Computer Science 2024-12-23 Albert Manuel Orozco Camacho , Stefan Horoi , Guy Wolf , Eugene Belilovsky

Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderation. However, the non-stationary nature of user data…

Machine Learning · Computer Science 2025-10-07 Yufei Li , Yu Fu , Yue Dong , Cong Liu

We address the Continual Learning (CL) problem, wherein a model must learn a sequence of tasks from non-stationary distributions while preserving prior knowledge upon encountering new experiences. With the advancement of foundation models,…

Machine Learning · Computer Science 2024-07-08 Kyra Ahrens , Hans Hergen Lehmann , Jae Hee Lee , Stefan Wermter

Continual model merging integrates independently fine-tuned models sequentially without access to the original training data, offering a scalable and efficient solution for continual learning. However, existing methods face two critical…

Machine Learning · Computer Science 2025-10-23 Zihuan Qiu , Yi Xu , Chiyuan He , Fanman Meng , Linfeng Xu , Qingbo Wu , Hongliang Li

The proliferation of pre-trained models has given rise to a wide array of specialised, fine-tuned models. Model merging aims to merge the distinct capabilities of these specialised models into a unified model, requiring minimal or even no…

Machine Learning · Computer Science 2025-12-23 Yayuan Li , Jian Zhang , Jintao Guo , Zihan Cheng , Lei Qi , Yinghuan Shi , Yang Gao

Given access to accurate dynamical models, modern planning approaches are effective in computing feasible and optimal plans for repetitive robotic tasks. However, it is difficult to model the true dynamics of the real world before…

Robotics · Computer Science 2020-10-19 Anirudh Vemula , J. Andrew Bagnell , Maxim Likhachev

Meta continual learning algorithms seek to train a model when faced with similar tasks observed in a sequential manner. Despite promising methodological advancements, there is a lack of theoretical frameworks that enable analysis of…

Machine Learning · Computer Science 2020-10-12 R. Krishnan , Prasanna Balaprakash

Multi-task learning (MTL) is a machine learning paradigm that aims to improve the generalization performance of a model on multiple related tasks by training it simultaneously on those tasks. Unlike MTL, where the model has instant access…

Machine Learning · Computer Science 2025-03-21 Amin Banayeeanzade , Mahdi Soltanolkotabi , Mohammad Rostami

Continual learning (CL) aims to extend deep models from static and enclosed environments to dynamic and complex scenarios, enabling systems to continuously acquire new knowledge of novel categories without forgetting previously learned…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Sunyuan Qiang , Xuxin Lin , Yanyan Liang , Jun Wan , Du Zhang

We present Preference Flow Matching (PFM), a new framework for preference-based reinforcement learning (PbRL) that streamlines the integration of preferences into an arbitrary class of pre-trained models. Existing PbRL methods require…

Machine Learning · Computer Science 2024-10-29 Minu Kim , Yongsik Lee , Sehyeok Kang , Jihwan Oh , Song Chong , Se-Young Yun

In this work, we study the problem of continual learning (CL) where the goal is to learn a model on a sequence of tasks, such that the data from the previous tasks becomes unavailable while learning on the current task data. CL is…

Machine Learning · Computer Science 2024-12-12 Imad Eddine Marouf , Subhankar Roy , Enzo Tartaglione , Stéphane Lathuilière