Related papers: Fine-Grained Model Merging via Modular Expert Reco…

Customization techniques for text-to-image models have paved the way for a wide range of previously unattainable applications, enabling the generation of specific concepts across diverse contexts and styles. While existing methods…

Merging multiple Low-Rank Adaptation (LoRA) experts into a single backbone is a promising approach for efficient multi-task deployment. While existing methods strive to alleviate interference via weight interpolation or subspace alignment,…

Model merging aims to build a multi-task learner by combining the parameters of individually fine-tuned models without additional training. While a straightforward approach is to average model parameters across tasks, this often results in…

Model merging combines expert models for multitask performance but faces challenges from parameter interference. This has sparked recent interest in controllable model merging, giving users the ability to explicitly balance performance…

Sparsely activated Mixture-of-Experts (SMoE) has shown promise to scale up the learning capacity of neural networks, however, they have issues like (a) High Memory Usage, due to duplication of the network layers into multiple copies as…

Recent large reasoning models (LRMs) have made substantial progress in complex reasoning tasks, yet they often generate lengthy reasoning paths for every query, incurring unnecessary computation and latency. Existing speed-up approaches…

With the rise and ubiquity of larger deep learning models, the need for high-quality compression techniques is growing in order to deploy these models widely. The sheer parameter count of these models makes it difficult to fit them into the…

Parameter efficient finetuning (PEFT) methods are widely used in LLMs and generative models in computer vision. Especially one can use multiple of these during inference to change the behavior of the base model. In this paper we…

In this study, we focus on heterogeneous knowledge transfer across entirely different model architectures, tasks, and modalities. Existing knowledge transfer methods (e.g., backbone sharing, knowledge distillation) often hinge on shared…

To address the performance limitations of the Segment Anything Model (SAM) in specific domains, existing works primarily adopt adapter-based one-step adaptation paradigms. However, some of these methods are specific developed for specific…

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 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…

Maintaining robust 3D perception under dynamic and unpredictable test-time conditions remains a critical challenge for autonomous driving systems. Existing test-time adaptation (TTA) methods often fail in high-variance tasks like 3D object…

During modeling of dynamical systems, often two or more model architectures are combined to obtain a more powerful or efficient model regarding a specific application area. This covers the combination of multiple machine learning…

The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computation significantly for large models, but its deployment can…

Model merging offers a training-free alternative to multi-task learning by combining independently fine-tuned models into a unified one without access to raw data. However, existing approaches often rely on heuristics to determine the…

Model merging under unseen test-time distribution shifts often renders naive strategies, such as mean averaging unreliable. This challenge is especially acute in medical imaging, where models are fine-tuned locally at clinics on private…

Mixture-of-Experts (MoE) model architectures can significantly reduce the number of activated parameters per token, enabling computationally efficient training and inference. However, their large overall parameter counts and model sizes…

Retrieval-augmented generation (RAG) has become the backbone of grounding Large Language Models (LLMs), improving knowledge updates and reducing hallucinations. Recently, LLM-based retriever models have shown state-of-the-art performance…

Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the output distributions of multiple models and selecting the most probable label. This idea…