Related papers: Model Merging in the Essential Subspace
Finite mixture models are powerful tools for modelling and analyzing heterogeneous data. Parameter estimation is typically carried out using maximum likelihood estimation via the Expectation-Maximization (EM) algorithm. Recently, the…
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…
Cross-study replicability is a powerful model evaluation criterion that emphasizes generalizability of predictions. When training cross-study replicable prediction models, it is critical to decide between merging and treating the studies…
As specialized large language models (LLMs) become increasingly prevalent, model merging methods are being used to combine them to create a single multi-task model without requiring any additional data or training. However, these approaches…
Scanning Transmission Electron Microscopy (STEM) coupled with Electron Energy Loss Spectroscopy (EELS) presents a powerful platform for detailed material characterization via rich imaging and spectroscopic data. Modern electron microscopes…
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…
Entity alignment is to find identical entities in different knowledge graphs. Although embedding-based entity alignment has recently achieved remarkable progress, training data insufficiency remains a critical challenge. Conventional…
Upon the significant performance of the supervised deep neural networks, conventional procedures of developing ML system are \textit{task-centric}, which aims to maximize the task accuracy. However, we scrutinized this \textit{task-centric}…
Model merging has emerged as a lightweight paradigm for enhancing Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. In this work, we analyze late-stage pre-training trajectories and uncover a…
The aim of this paper is to deal with multi-physics simulation of micro-electro-mechanical systems (MEMS) based on an advanced numerical methodology. MEMS are very small devices in which electric as well as mechanical and fluid phenomena…
Edge computing has emerged as an alternative to reduce transmission and processing delay and preserve privacy of the video streams. However, the ever-increasing complexity of Deep Neural Networks (DNNs) used in video-based applications…
Shared embedding spaces are widely used for multimodal search and data curation. In practice, two problems often limit how well this works. First, embeddings can reflect modality more than meaning, so examples cluster by input type even…
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…
A surface integral representation of Maxwell's equations allows the efficient electromagnetic (EM) modeling of three-dimensional structures with a two-dimensional discretization, via the boundary element method (BEM). However, existing BEM…
Expectation maximisation (EM) is an unsupervised learning method for estimating the parameters of a finite mixture distribution. It works by introducing "hidden" or "latent" variables via Baum's auxiliary function $Q$ that allow the joint…
Multi-modality image fusion is a technique that combines information from different sensors or modalities, enabling the fused image to retain complementary features from each modality, such as functional highlights and texture details.…
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…
Deep convolutional neural networks achieve remarkable performance by exhaustively processing dense spatial feature maps, yet this brute-force strategy introduces significant computational redundancy and encourages reliance on spurious…
In Earth System Modeling (ESM), meshes of different models usually do not match, requiring data mapping algorithms implemented in coupling software. Valcke et al. recently introduced a benchmark to evaluate such algorithms and compared…
Continual Learning (CL) strives to learn incrementally across tasks while mitigating catastrophic forgetting. A key challenge in CL is balancing stability (retaining prior knowledge) and plasticity (learning new tasks). While representative…