相关论文: Ortho-Hydra: Orthogonalized Experts for DiT LoRA

Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of Large Language Models (LLMs), and recent Mixture-of-Experts (MoE) extensions further enhance flexibility by dynamically combining multiple LoRA experts. However, existing…

Mixture-of-Experts (MoE) models scale capacity efficiently, but their massive parameter footprint creates a deployment-time memory bottleneck. We organize retraining-free MoE compression into three paradigms - Expert Pruning, Expert…

Recent research arXiv:2410.15027 has explored the use of diffusion transformers (DiTs) for task-agnostic image generation by simply concatenating attention tokens across images. However, despite substantial computational resources, the…

Vision Transformers (ViTs) have been widely adopted in vision tasks due to their strong transferability. In Federated Learning (FL), where full fine-tuning is communication heavy, Low-Rank Adaptation (LoRA) provides an efficient and…

Attention is all we need as long as we have enough data. Even so, it is sometimes not easy to determine how much data is enough while the models are becoming larger and larger. In this paper, we propose HYDRA heads, lightweight pretrained…

Learning from non-stationary data streams subject to concept drift requires models that can adapt on-the-fly while remaining resource-efficient. Existing adaptive ensemble methods often rely on coarse-grained adaptation mechanisms or simple…

The goal of this paper is to improve (upcycle) an existing large language model without the prohibitive requirements of continued pre-training of the full-model. The idea is to split the pre-training data into semantically relevant groups…

Diffusion policies are competitive for offline reinforcement learning (RL) but are typically guided at sampling time by heuristics that lack a statistical notion of risk. We introduce LRT-Diffusion, a risk-aware sampling rule that treats…

Modern Mixture-of-Experts (MoE) architectures allocate expert capacity through a rigid per-layer rule: each transformer layer owns a separate expert set. This convention couples depth scaling with linear expert-parameter growth and assumes…

Exponential growth in the scale of modern foundation models has led to the widespread adoption of Low-Rank Adaptation (LoRA) as a parameter-efficient fine-tuning technique. However, standard LoRA implementations disregard the varying…

Fine-tuning models via Low-Rank Adaptation (LoRA) demonstrates remarkable performance in subject-driven or style-driven generation tasks. Studies have explored combinations of different LoRAs to jointly generate learned styles and content.…

Large Language Models (LLMs) process every token through all layers of a transformer stack, causing wasted computation on simple queries and insufficient flexibility for harder ones that need deeper reasoning. Adaptive-depth methods can…

Ensembles of models have been empirically shown to improve predictive performance and to yield robust measures of uncertainty. However, they are expensive in computation and memory. Therefore, recent research has focused on distilling…

The Error Diffusion Learning Algorithm (EDLA) is a learning scheme that performs synaptically local weight updates driven by a single, globally defined error signal. Although originally proposed as an alternative to backpropagation, its…

Fine-tuning has become a popular approach to adapting large foundational models to specific tasks. As the size of models and datasets grows, parameter-efficient fine-tuning techniques are increasingly important. One of the most widely used…

Federated learning systems have been identified as an efficient approach to scaling distributed model training with a large amount of participants or data owners while guaranteeing data privacy. To apply the current most popular pre-trained…

Despite recent advances in photorealistic image generation through large-scale models like FLUX and Stable Diffusion v3, the practical deployment of these architectures remains constrained by their inherent intractability to parameter…

Parameter-efficient fine-tuning(PEFT) has largely focused on LoRA and its accuracy-oriented variants, leaving the original goal of reducing trainable parameters has receivedcomparatively little attention. We introduce FoRA, which revisits…

Foundation models (FMs) adapt well to specific domains or tasks with fine-tuning, and federated learning (FL) enables the potential for privacy-preserving fine-tuning of the FMs with on-device local data. For federated fine-tuning of FMs,…

Recently, large language models (LLMs) have achieved remarkable breakthroughs, revolutionizing the natural language processing domain and beyond. Due to immense parameter sizes, fine-tuning these models with private data for diverse…