English
Related papers

Related papers: Revisiting Model Interpolation for Efficient Reaso…

200 papers

Large Reasoning Models (LRMs) excel in structured tasks by emulating deliberate human reasoning but often suffer from overthinking, degrading performance and wasting resources. One possible baseline is to deploy both LLM and LRM, then route…

Computation and Language · Computer Science 2025-10-09 Jaeseong Lee , Dayoung Kwon , seung-won hwang

Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged…

Machine Learning · Computer Science 2026-02-09 Haiyun Qiu , Xingyu Wu , Liang Feng , Kay Chen Tan

The "alignment tax" of post-training is typically framed as a drop in task accuracy. We show it also involves a severe loss of calibration, making models overconfident, less reliable, and model outputs less diverse. We show that this…

Computation and Language · Computer Science 2025-11-03 Tiancheng Hu , Benjamin Minixhofer , Nigel Collier

We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks…

Computer Vision and Pattern Recognition · Computer Science 2018-05-15 Yi-Min Chou , Yi-Ming Chan , Jia-Hong Lee , Chih-Yi Chiu , Chu-Song Chen

Model merging, such as model souping, is the practice of combining different models with the same architecture together without further training. In this work, we present a model merging methodology that addresses the difficulty of…

Computation and Language · Computer Science 2025-05-27 Lucas Bandarkar , Benjamin Muller , Pritish Yuvraj , Rui Hou , Nayan Singhal , Hongjiang Lv , Bing Liu

Being prompted to engage in reasoning has emerged as a core technique for using large language models (LLMs), deploying additional inference-time compute to improve task performance. However, as LLMs increase in both size and adoption,…

Computation and Language · Computer Science 2025-06-25 C. Nicolò De Sabbata , Theodore R. Sumers , Badr AlKhamissi , Antoine Bosselut , Thomas L. Griffiths

Deep learning is very effective at jointly learning feature representations and classification models, especially when dealing with high dimensional input patterns. Probabilistic logic reasoning, on the other hand, is capable to take…

Machine Learning · Computer Science 2019-01-15 Giuseppe Marra , Francesco Giannini , Michelangelo Diligenti , Marco Gori

Model merging provides a cost-effective and data-efficient combination of specialized deep neural networks through parameter integration. This technique leverages expert models across downstream tasks without requiring retraining. Most…

Machine Learning · Computer Science 2025-10-17 Levy Chaves , Eduardo Valle , Sandra Avila

In this work, we introduce DUET (Dual-model Efficient Two-stage inference), a collaborative inference framework in which a capable model and a lightweight model work together to solve a task. Relying on a single large model to perform…

Machine Learning · Computer Science 2026-05-05 Yilei Chen , Sharut Gupta , Yannis Paschalidis , Ayush Sekhari , Aldo Pacchiano

Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data. Existing methods attempt to alleviate task conflicts by sparsifying task vectors or promoting orthogonality…

Machine Learning · Computer Science 2025-05-27 Yongxian Wei , Anke Tang , Li Shen , Zixuan Hu , Chun Yuan , Xiaochun Cao

Model merging combines multiple fine-tuned checkpoints into a single model without additional training, offering an attractive approach to reusing models and efficiently improving performance. However, it remains unclear whether the…

Computation and Language · Computer Science 2026-03-31 Oğuz Kağan Hitit , Leander Girrbach , Zeynep Akata

A retrieval model should not only interpolate the training data but also extrapolate well to the queries that are different from the training data. While neural retrieval models have demonstrated impressive performance on ad-hoc search…

Information Retrieval · Computer Science 2022-08-05 Jingtao Zhan , Xiaohui Xie , Jiaxin Mao , Yiqun Liu , Jiafeng Guo , Min Zhang , Shaoping Ma

Model merging has gained increasing attention due to its intriguing property: interpolating the parameters of different task-specific fine-tuned models leads to multi-task abilities. However, despite its empirical success, the underlying…

Artificial Intelligence · Computer Science 2025-06-24 Zijun Chen , Zhanpeng Zhou , Bo Zhang , Weinan Zhang , Xi Sun , Junchi Yan

As large language models (LLMs) have gained popularity for a variety of use cases, making them adaptable and controllable has become increasingly important, especially for user-facing applications. While the existing literature on LLM…

Computation and Language · Computer Science 2025-09-30 Sara Kangaslahti , David Alvarez-Melis

Scaling model size and training data has led to great advances in the performance of Large Language Models (LLMs). However, the diminishing returns of this approach necessitate alternative methods to improve model capabilities, particularly…

Machine Learning · Computer Science 2025-11-05 Daman Arora , Andrea Zanette

Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered…

Computation and Language · Computer Science 2023-11-07 Zeming Chen , Gail Weiss , Eric Mitchell , Asli Celikyilmaz , Antoine Bosselut

In current Large Language Models we can trust the production of smoothly flowing prose on the basis of the principles of machine learning. However, there is no comparably principled basis to justify trust in the content of the text…

Artificial Intelligence · Computer Science 2026-05-15 Leslie G. Valiant

Model merging enables powerful capabilities in neural networks without requiring additional training. In this paper, we introduce a novel perspective on model merging by leveraging the fundamental mechanisms of neural network…

Machine Learning · Computer Science 2025-09-19 Haiquan Qiu , You Wu , Dong Li , Jianmin Guo , Quanming Yao

Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to retain prior knowledge. While existing approaches attempt to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Ghada Sokar , Gintare Karolina Dziugaite , Anurag Arnab , Ahmet Iscen , Pablo Samuel Castro , Cordelia Schmid

Imitation learning with visual observations is notoriously inefficient when addressed with end-to-end behavioural cloning methods. In this paper, we explore an alternative paradigm which decomposes reasoning into three phases. First, a…

Robotics · Computer Science 2023-12-20 Norman Di Palo , Edward Johns