Related papers: DC-Merge: Improving Model Merging with Directional…

Model merging aims to integrate multiple expert models into a single model that inherits their complementary strengths without incurring the inference-time cost of ensembling. Recent progress has shown that merging can be highly effective…

Due to limitations in data quality, some essential visual tasks are difficult to perform independently. Introducing previously unavailable information to transfer informative dark knowledge has been a common way to solve such hard tasks.…

In Continual Learning (CL), a model is required to learn a stream of tasks sequentially without significant performance degradation on previously learned tasks. Current approaches fail for a long sequence of tasks from diverse domains and…

Large Language Models (LLMs) have been adopted and deployed worldwide for a broad variety of applications. However, ensuring their safe use remains a significant challenge. Preference training and safety measures often overfit to harms…

Efficiently merging several models fine-tuned for different tasks, but stemming from the same pretrained base model, is of great practical interest. Despite extensive prior work, most evaluations of model merging in computer vision are…

Model merging offers an effective strategy to combine the strengths of multiple finetuned models into a unified model that preserves the specialized capabilities of each. Existing methods merge models in a global manner, performing…

Multi-task learning (MTL) has been widely adopted for its ability to simultaneously learn multiple tasks. While existing gradient manipulation methods often yield more balanced solutions than simple scalarization-based approaches, they…

During the last decades, learning a low-dimensional space with discriminative information for dimension reduction (DR) has gained a surge of interest. However, it's not accessible for these DR methods to achieve satisfactory performance…

Model merging has attracted attention as an effective path toward multi-task adaptation by integrating knowledge from multiple task-specific models. Among existing approaches, dynamic merging mitigates performance degradation caused by…

Model merging has emerged as a promising approach for unifying independently fine-tuned models into an integrated framework, significantly enhancing computational efficiency in multi-task learning. Recently, several SVD-based techniques…

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…

Model ensemble is an effective strategy in continual learning, which alleviates catastrophic forgetting by interpolating model parameters, achieving knowledge fusion learned from different tasks. However, existing model ensemble methods…

Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses…

As an effective approach to equip models with multi-task capabilities without additional training, model merging has garnered significant attention. However, existing methods face challenges of redundant parameter conflicts and the…

Continual Learning (CL) aims to enable Deep Neural Networks (DNNs) to learn new data without forgetting previously learned knowledge. The key to achieving this goal is to avoid confusion at the feature level, i.e., avoiding confusion within…

Meta learning recently has been heavily researched and helped advance the contemporary machine learning. However, achieving well-performing meta-learning model requires a large amount of training tasks with high-quality meta-data…

Dataset Condensation (DC) aims to reduce deep neural networks training efforts by synthesizing a small dataset such that it will be as effective as the original large dataset. Conventionally, DC relies on a costly bi-level optimization…

Inverse problems are inherently ill-posed, suffering from non-uniqueness and instability. Classical regularization methods provide mathematically well-founded solutions, ensuring stability and convergence, but often at the cost of reduced…

Vision-Language Models (VLMs) combine visual perception with the general capabilities, such as reasoning, of Large Language Models (LLMs). However, the mechanisms by which these two abilities can be combined and contribute remain poorly…

Weight-space model merging combines independently fine-tuned models without accessing original training data, offering a practical alternative to joint training. While merging succeeds in multitask settings, its behavior in multilingual…