English
Related papers

Related papers: Model Merging Improves Zero-Shot Generalization in…

200 papers

Land-use and land cover (LULC) analysis is critical in remote sensing, with wide-ranging applications across diverse fields such as agriculture, utilities, and urban planning. However, automating LULC map generation using machine learning…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Sparsh Pekhale , Rakshith Sathish , Sathisha Basavaraju , Divya Sharma

Large Language Models (LLMs) remain heavily centered on English, with limited performance in low-resource languages. Existing adaptation approaches, such as continual pre-training, demand significant computational resources. In the case of…

Computation and Language · Computer Science 2026-03-31 Eneko Valero , Maria Ribalta i Albado , Oscar Sainz , Naiara Perez , German Rigau

Achieving balanced alignment of large language models (LLMs) in terms of Helpfulness, Honesty, and Harmlessness (3H optimization) constitutes a cornerstone of responsible AI. Existing methods like data mixture strategies face limitations,…

Computation and Language · Computer Science 2026-02-03 Jinluan Yang , Dingnan Jin , Anke Tang , Li Shen , Didi Zhu , Zhengyu Chen , Ziyu Zhao , Daixin Wang , Qing Cui , Zhiqiang Zhang , Jun Zhou , Fei Wu , Kun Kuang

Recent breakthroughs in large language models (LLMs) offer unprecedented natural language understanding and generation capabilities. However, existing surveys on LLMs in biomedicine often focus on specific applications or model…

Model merging aims to efficiently combine the weights of multiple expert models, each trained on a specific task, into a single multi-task model, with strong performance across all tasks. When applied to all but the last layer of weights,…

Machine Learning · Computer Science 2024-10-17 Ekansh Sharma , Daniel M. Roy , Gintare Karolina Dziugaite

In this paper, we study multi-target domain adaptation of scene understanding models. While previous methods achieved commendable results through inter-domain consistency losses, they often assumed unrealistic simultaneous access to images…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Wenyi Li , Huan-ang Gao , Mingju Gao , Beiwen Tian , Rong Zhi , Hao Zhao

Diffusion models for image generation often exhibit a trade-off between perceptual sample quality and data likelihood: training objectives emphasizing high-noise denoising steps yield realistic images but poor likelihoods, whereas…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Yasin Esfandiari , Stefan Bauer , Sebastian U. Stich , Andrea Dittadi

Deformable registration is a fundamental task in medical image processing, aiming to achieve precise alignment by establishing nonlinear correspondences between images. Traditional methods offer good adaptability and interpretability but…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Jing Hu , Kaiwei Yu , Hongjiang Xian , Shu Hu , Xin Wang

We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to…

Computation and Language · Computer Science 2025-10-24 Bowen Wang , Haiyuan Wan , Liwen Shi , Chen Yang , Peng He , Yue Ma , Haochen Han , Wenhao Li , Tiao Tan , Yongjian Li , Fangming Liu , Yifan Gong , Sheng Zhang

Reasoning capabilities represent a critical frontier for large language models (LLMs), but developing them requires extensive proprietary datasets and computational resources. One way to efficiently supplement capabilities with is by model…

Artificial Intelligence · Computer Science 2025-06-26 Guinan Su , Jonas Geiping

Multilingual Large Language Models (LLMs) achieve remarkable levels of zero-shot cross-lingual transfer performance. We speculate that this is predicated on their ability to align languages without explicit supervision from parallel…

Computation and Language · Computer Science 2024-06-21 Hetong Wang , Pasquale Minervini , Edoardo M. Ponti

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…

Machine Learning · Computer Science 2025-04-04 Artyom Gadetsky , Andrei Atanov , Yulun Jiang , Zhitong Gao , Ghazal Hosseini Mighan , Amir Zamir , Maria Brbic

We study how features emerge, disappear, and persist across models fine-tuned on different domains of text. More specifically, we start from a base one-layer Transformer language model that is trained on a combination of the BabyLM corpus,…

Computation and Language · Computer Science 2024-10-17 Niels Horn , Desmond Elliott

While training large language models (LLMs) from scratch can generate models with distinct functionalities and strengths, it comes at significant costs and may result in redundant capabilities. Alternatively, a cost-effective and compelling…

Computation and Language · Computer Science 2024-01-23 Fanqi Wan , Xinting Huang , Deng Cai , Xiaojun Quan , Wei Bi , Shuming Shi

The potential for zero-shot generalization in vision-language (V-L) models such as CLIP has spurred their widespread adoption in addressing numerous downstream tasks. Previous methods have employed test-time prompt tuning to adapt the model…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 Anant Khandelwal

Understanding alignment techniques begins with comprehending zero-shot generalization brought by instruction tuning, but little of the mechanism has been understood. Existing work has largely been confined to the task level, without…

Computation and Language · Computer Science 2025-04-08 Bingxiang He , Ning Ding , Cheng Qian , Jia Deng , Ganqu Cui , Lifan Yuan , Haiwen Hong , Huan-ang Gao , Longtao Huang , Hui Xue , Huimin Chen , Zhiyuan Liu , Maosong Sun

Fine-tuning pre-trained models provides significant advantages in downstream performance. The ubiquitous nature of pre-trained models such as BERT and its derivatives in natural language processing has also led to a proliferation of…

Computation and Language · Computer Science 2024-05-06 Thennal D K , Ganesh Nathan , Suchithra M S

A new paradigm for machine translation has recently emerged: fine-tuning large language models (LLM) on parallel text has been shown to outperform dedicated translation systems trained in a supervised fashion on much larger amounts of…

Computation and Language · Computer Science 2024-06-03 Aquia Richburg , Marine Carpuat

Recent work on permutation-based model merging has shown impressive low- or zero-barrier mode connectivity between models from completely different initializations. However, this line of work has not yet extended to the Transformer…

Computation and Language · Computer Science 2024-12-17 Neha Verma , Maha Elbayad

Large pretrained Transformer language models have been shown to exhibit zero-shot generalization, i.e. they can perform a wide variety of tasks that they were not explicitly trained on. However, the architectures and pretraining objectives…

Computation and Language · Computer Science 2022-04-13 Thomas Wang , Adam Roberts , Daniel Hesslow , Teven Le Scao , Hyung Won Chung , Iz Beltagy , Julien Launay , Colin Raffel