English
Related papers

Related papers: MoR: Mixture Of Representations For Mixed-Precisio…

200 papers

Many data representations are vectors of continuous values. In particular, deep learning embeddings are data-driven representations, typically either unconstrained in Euclidean space, or constrained to a hypersphere. These may also be…

Machine Learning · Computer Science 2026-03-04 Dan Stowell

Quantization method plays a crucial role in improving model efficiency and reducing deployment costs, enabling the widespread application of deep learning models on resource-constrained devices. However, the quantization process inevitably…

Machine Learning · Computer Science 2025-09-30 Jinhao Zhang , Yunquan Zhang , Boyang Zhang , Zeyu Liu , Daning Cheng

Parametric model order reduction (pMOR) is a powerful tool for accelerating finite element (FE) simulations while maintaining parametric dependencies. For geometric parameters, pMOR by matrix interpolation is a well-suited approach because…

Numerical Analysis · Mathematics 2025-12-18 Sebastian Resch-Schopper , Romain Rumpler , Gerhard Müller

Multimodal instruction tuning has proven to be an effective strategy for achieving zero-shot generalization by fine-tuning pre-trained Large Multimodal Models (LMMs) with instruction-following data. However, as the scale of LMMs continues…

Advancements in deep learning are driven by training models with increasingly larger numbers of parameters, which in turn heightens the computational demands. To address this issue, Mixture-of-Depths (MoD) models have been proposed to…

Computer Vision and Pattern Recognition · Computer Science 2024-12-31 Advait Gadhikar , Souptik Kumar Majumdar , Niclas Popp , Piyapat Saranrittichai , Martin Rapp , Lukas Schott

The Mixture of Experts (MoE) architecture is an important method for scaling Large Language Models (LLMs). It increases model capacity while keeping computation cost low. However, the ultra-large MoE models still have hundreds of billions…

Artificial Intelligence · Computer Science 2025-10-01 Yixiao Chen , Yanyue Xie , Ruining Yang , Wei Jiang , Wei Wang , Yong He , Yue Chen , Pu Zhao , Yanzhi Wang

Linear sequence modeling methods, such as linear attention, state space modeling, and linear RNNs, offer significant efficiency improvements by reducing the complexity of training and inference. However, these methods typically compress the…

Computation and Language · Computer Science 2025-11-19 Jusen Du , Weigao Sun , Disen Lan , Jiaxi Hu , Yu Cheng

Multiple modalities can provide more valuable information than single one by describing the same contents in various ways. Hence, it is highly expected to learn effective joint representation by fusing the features of different modalities.…

Computer Vision and Pattern Recognition · Computer Science 2018-10-09 Di Hu , Feiping Nie , Xuelong Li

Based on the model's resilience to computational noise, model quantization is important for compressing models and improving computing speed. Existing quantization techniques rely heavily on experience and "fine-tuning" skills. In the…

Machine Learning · Computer Science 2022-07-22 Daning Cheng , Wenguang Chen

The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, and editability. However, a major challenge lies in the…

Computer Vision and Pattern Recognition · Computer Science 2024-10-18 James Oldfield , Markos Georgopoulos , Grigorios G. Chrysos , Christos Tzelepis , Yannis Panagakis , Mihalis A. Nicolaou , Jiankang Deng , Ioannis Patras

Mixtures-of-Experts (MoE) are conditional mixture models that have shown their performance in modeling heterogeneity in data in many statistical learning approaches for prediction, including regression and classification, as well as for…

Methodology · Statistics 2019-07-17 Bao Tuyen Huynh , Faicel Chamroukhi

Mixture-of-Experts (MoE) layers have emerged as an important tool in scaling up modern neural networks by decoupling total trainable parameters from activated parameters in the forward pass for each token. However, sparse MoEs add…

Machine Learning · Computer Science 2026-05-22 Tianze Jiang , Blake Bordelon , Cengiz Pehlevan , Boris Hanin

Model merging has recently emerged as a lightweight alternative to ensembling, combining multiple fine-tuned models into a single set of parameters with no additional training overhead. Yet, existing merging methods fall short of matching…

Multi-modal MRIs are widely used in neuroimaging applications since different MR sequences provide complementary information about brain structures. Recent works have suggested that multi-modal deep learning analysis can benefit from…

Computer Vision and Pattern Recognition · Computer Science 2021-06-14 Jiahong Ouyang , Ehsan Adeli , Kilian M. Pohl , Qingyu Zhao , Greg Zaharchuk

We propose a federated methodology to learn low-dimensional representations from a dataset that is distributed among several clients. In particular, we move away from the commonly-used cross-entropy loss in federated learning, and seek to…

Machine Learning · Computer Science 2022-10-04 Juan Cervino , Navid NaderiAlizadeh , Alejandro Ribeiro

Retrieving evidences from tabular and textual resources is essential for open-domain question answering (OpenQA), which provides more comprehensive information. However, training an effective dense table-text retriever is difficult due to…

Computation and Language · Computer Science 2022-10-14 Junjie Huang , Wanjun Zhong , Qian Liu , Ming Gong , Daxin Jiang , Nan Duan

Deep neural networks have enabled progress in a wide variety of applications. Growing the size of the neural network typically results in improved accuracy. As model sizes grow, the memory and compute requirements for training these models…

As foundational models reshape scientific discovery, a bottleneck persists in dynamical system reconstruction (DSR): the ability to learn across system hierarchies. Many meta-learning approaches have been applied successfully to single…

Machine Learning · Computer Science 2025-06-12 Roussel Desmond Nzoyem , Grant Stevens , Amarpal Sahota , David A. W. Barton , Tom Deakin

Recently, diffusion models have achieved a great performance with a small dataset of size $n$ and a fast optimization process. However, the estimation error of diffusion models suffers from the curse of dimensionality $n^{-1/D}$ with the…

Machine Learning · Computer Science 2026-01-06 Ruofeng Yang , Yongcan Li , Bo Jiang , Cheng Chen , Shuai Li

Dense retrieval models usually adopt vectors from the last hidden layer of the document encoder to represent a document, which is in contrast to the fact that representations in different layers of a pre-trained language model usually…

Information Retrieval · Computer Science 2025-09-30 Zhongbin Xie , Thomas Lukasiewicz