English
Related papers

Related papers: MIN-Merging: Merge the Important Neurons for Model…

200 papers

Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques. Such model-based methods utilize mathematical formulations that represent the underlying physics, prior information and…

Signal Processing · Electrical Eng. & Systems 2022-09-13 Nir Shlezinger , Jay Whang , Yonina C. Eldar , Alexandros G. Dimakis

Sparse Mixture-of-Experts (SMoE) architectures are widely used in large language models (LLMs) due to their computational efficiency. However, though only a few experts are activated for each token, SMoE still requires loading all expert…

Computation and Language · Computer Science 2025-09-15 Yixiao Zhou , Ziyu Zhao , Dongzhou Cheng , zhiliang wu , Jie Gui , Yi Yang , Fei Wu , Yu Cheng , Hehe Fan

In this work, we aim to solve data-driven optimization problems, where the goal is to find an input that maximizes an unknown score function given access to a dataset of inputs with corresponding scores. When the inputs are high-dimensional…

Machine Learning · Computer Science 2020-01-01 Aviral Kumar , Sergey Levine

Besides training, mathematical optimization is also used in deep learning to model and solve formulations over trained neural networks for purposes such as verification, compression, and optimization with learned constraints. However,…

Optimization and Control · Mathematics 2024-01-30 Jiatai Tong , Junyang Cai , Thiago Serra

Recent advances in deep learning optimization showed that, with some a-posteriori information on fully-trained models, it is possible to match the same performance by simply training a subset of their parameters. Such a discovery has a…

Machine Learning · Computer Science 2022-11-15 Andrea Bragagnolo , Enzo Tartaglione , Marco Grangetto

In this paper, we will introduce a novel deep model named Reconciled Polynomial Network (RPN) for deep function learning. RPN has a very general architecture and can be used to build models with various complexities, capacities, and levels…

Machine Learning · Computer Science 2024-07-09 Jiawei Zhang

Model compression is essential in the deployment of large Computer Vision models on embedded devices. However, static optimization techniques (e.g. pruning, quantization, etc.) neglect the fact that different inputs have different…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Fabio Montello , Ronja Güldenring , Simone Scardapane , Lazaros Nalpantidis

Ensemble learning is a widespread technique to improve the prediction performance of neural networks. However, it comes at the price of increased memory and inference time. In this work we propose a novel model fusion technique called…

Machine Learning · Computer Science 2025-02-12 Muhammed Öz , Nicholas Kiefer , Charlotte Debus , Jasmin Hörter , Achim Streit , Markus Götz

Deep-learning-based methods for different applications have been shown vulnerable to adversarial examples. These examples make deployment of such models in safety-critical tasks questionable. Use of deep neural networks as inverse problem…

Machine Learning · Computer Science 2020-02-28 Ankit Raj , Yoram Bresler , Bo Li

Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In…

Computation and Language · Computer Science 2019-09-04 Han Cheol Moon , Tasnim Mohiuddin , Shafiq Joty , Xu Chi

Thanks to their universal approximation properties and new efficient training strategies, Deep Neural Networks are becoming a valuable tool for the approximation of mathematical operators. In the present work, we introduce Mesh-Informed…

Numerical Analysis · Mathematics 2023-05-08 Nicola Rares Franco , Andrea Manzoni , Paolo Zunino

Foundation models and their checkpoints have significantly advanced deep learning, boosting performance across various applications. However, fine-tuned models often struggle outside their specific domains and exhibit considerable…

Monotonicity constraints are powerful regularizers in statistical modelling. They can support fairness in computer-aided decision making and increase plausibility in data-driven scientific models. The seminal min-max (MM) neural network…

Machine Learning · Computer Science 2024-05-28 Christian Igel

Mixed-precision Deep Neural Networks achieve the energy efficiency and throughput needed for hardware deployment, particularly when the resources are limited, without sacrificing accuracy. However, the optimal per-layer bit precision that…

Machine Learning · Computer Science 2022-08-15 Mariam Rakka , Mohammed E. Fouda , Pramod Khargonekar , Fadi Kurdahi

Deep convolutional neural networks (DCNNs) have become the state-of-the-art (SOTA) approach for many computer vision tasks: image classification, object detection, semantic segmentation, etc. However, most SOTA networks are too large for…

Computer Vision and Pattern Recognition · Computer Science 2022-10-26 Alireza Azadbakht , Saeed Reza Kheradpisheh , Ismail Khalfaoui-Hassani , Timothée Masquelier

Biological multimodal large language models (MLLMs) have emerged as powerful foundation models for scientific discovery. However, existing models are specialized to a single modality, limiting their ability to solve inherently cross-modal…

Machine Learning · Computer Science 2026-03-17 Wonbin Lee , Dongki Kim , Sung Ju Hwang

We derive a new margin-based regularization formulation, termed multi-margin regularization (MMR), for deep neural networks (DNNs). The MMR is inspired by principles that were applied in margin analysis of shallow linear classifiers, e.g.,…

Machine Learning · Computer Science 2020-09-15 Berry Weinstein , Shai Fine , Yacov Hel-Or

This paper reports a novel deep architecture referred to as Maxout network In Network (MIN), which can enhance model discriminability and facilitate the process of information abstraction within the receptive field. The proposed network…

Computer Vision and Pattern Recognition · Computer Science 2015-11-10 Jia-Ren Chang , Yong-Sheng Chen

Reinforcement Learning with Verifiable Rewards (RLVR) plays a key role in stimulating the explicit reasoning capability of Large Language Models (LLMs). We can achieve expert-level performance in some specific domains via RLVR, such as…

Artificial Intelligence · Computer Science 2026-03-12 Haoqing Wang , Xiang Long , Ziheng Li , Yilong Xu , Tingguang Li , Yehui Tang

Large language models, such as ChatGPT, Claude, or LLaMA, are gigantic, monolithic, and possess the superpower to simultaneously support thousands of tasks. However, high-throughput applications often prefer smaller task-specific models…

Computation and Language · Computer Science 2025-02-17 Haoyu Yang , Zheng Zhang , Saket Sathe