Related papers: Unlocking the Potential of Continual Model Merging…
Continuous-time neural processes are performant sequential decision-makers that are built by differential equations (DE). However, their expressive power when they are deployed on computers is bottlenecked by numerical DE solvers. This…
Multi-object tracking (MOT) is a fundamental task in computer vision that requires continuously tracking multiple targets while maintaining consistent identities across frames. However, most existing approaches primarily rely on…
Deep model fusion/merging is an emerging technique that merges the parameters or predictions of multiple deep learning models into a single one. It combines the abilities of different models to make up for the biases and errors of a single…
Multimodal Continual Instruction Tuning (MCIT) is essential for sequential task adaptation of Multimodal Large Language Models (MLLMs) but is severely restricted by catastrophic forgetting. While existing literature focuses on the reasoning…
Model merging has achieved significant success, with numerous innovative methods proposed to enhance capabilities by combining multiple models. However, challenges persist due to the lack of a unified framework for classification and…
Advances in machine learning methods for computer vision tasks have led to their consideration for safety-critical applications like autonomous driving. However, effectively integrating these methods into the automotive development…
The pre-trained language models are continually fine-tuned to better support downstream applications. However, this operation may result in significant performance degeneration on general tasks beyond the targeted domain. To overcome this…
Online Class-Incremental Learning (OCIL) enables models to learn continuously from non-i.i.d. data streams. Since samples of the data streams can be seen only once, it is more suitable for real-world scenarios compared to offline learning.…
The convergence of IoT, Edge, Cloud, and HPC technologies creates a compute continuum that merges cloud scalability and flexibility with HPC's computational power and specialized optimizations. However, integrating cloud and HPC resources…
Software reuse has long been recognized as a critical and widely studied topic in software engineering, offering substantial benefits in reducing development costs, improving software quality, and enhancing operational efficiency. This…
Towards more general and human-like intelligence, large language models should seamlessly integrate both multilingual and multimodal capabilities; however, extending an existing multimodal model to many languages typically requires…
Mixture-of-experts (MoE) architectures could achieve impressive computational efficiency with expert parallelism, which relies heavily on all-to-all communication across devices. Unfortunately, such communication overhead typically…
Model merging, which combines multiple models into a single model, has gained popularity in recent years. By efficiently integrating the capabilities of various models, this significantly reduces the parameter count and memory usage.…
The standardization of clinical data elements (CDEs) aims to ensure consistent and comprehensive patient information across various healthcare systems. Existing methods often falter when standardizing CDEs of varying representation and…
Formally capturing the transition from a continuous model to a discrete model is investigated using model based refinement techniques. A very simple model for stopping (eg. of a train) is developed in both the continuous and discrete…
Controlling continuous-time dynamical systems is generally a two step process: first, identify or model the system dynamics with differential equations, then, minimize the control objectives to achieve optimal control function and optimal…
Model merging has emerged as a promising technique for enhancing large language models, though its application in large-scale pre-training remains relatively unexplored. In this paper, we present a comprehensive investigation of model…
Machine learning (ML) can be used in various ways to improve multi-user multiple-input multiple-output (MU-MIMO) receive processing. Typical approaches either augment a single processing step, such as symbol detection, or replace multiple…
To accommodate real-world dynamics, artificial intelligence systems need to cope with sequentially arriving content in an online manner. Beyond regular Continual Learning (CL) attempting to address catastrophic forgetting with offline…
There is a pressing need for better development methods and tools to keep up with the growing demand and increasing complexity of new software systems. New types of user interfaces, the need for intelligent components, sustainability…