Related papers: Exploring Data-Free LoRA Transferability for Video…

Traditional parameter-efficient fine-tuning (PEFT) methods such as LoRA are tightly coupled with the base model architecture, which constrains their applicability across heterogeneous pretrained large language models (LLMs). To address this…

Our understanding of vibrations in solids currently rests on concepts and techniques designed for crystals and explicitly relying on periodicity, hence inapplicable to amorphous materials. As a consequence, no established framework enables…

Diffusion Transformers currently lead the field in high-quality video generation, but their slow iterative denoising process and prohibitive quadratic attention costs for long sequences create significant inference bottlenecks. While both…

Model merging combines independently fine-tuned checkpoints without joint multi-task training. In the era of foundation-model, fine-tuning with Low-Rank Adaptation (LoRA) is prevalent, making LoRA merging a promising target. Existing…

Merging or routing low-rank adapters (LoRAs) has emerged as a popular solution for enhancing large language models, particularly when data access is restricted by regulatory or domain-specific constraints. This position paper argues that…

Diffusion models have achieved remarkable success in image generation, yet their deployment remains constrained by the heavy computational cost and the need for numerous inference steps. Previous efforts on fewer-step distillation attempt…

We study distillation for large language models under explicit compute constraints, with the goal of producing student models that are not only cheaper to train, but structurally efficient at inference time. While prior approaches to…

Recent advances in large-scale text-to-image diffusion models have heightened concerns about their potential misuse, especially in generating harmful or misleading content. This underscores the urgent need for effective machine unlearning,…

Consistent improvement of image priors over the years has led to the development of better inverse problem solvers. Diffusion models are the newcomers to this arena, posing the strongest known prior to date. Recently, such models operating…

Continual learning for vision-language models has achieved remarkable performance through synthetic replay, where samples are generated using Stable Diffusion to regularize during finetuning and retain knowledge. However, real-world…

In this paper, we review the key figures of merit to assess the performance of advanced random access (RA) schemes exploiting physical layer coding, repetitions and collision resolution techniques. We then investigate RA modeling aspects…

Deep learning has achieved some success in addressing the challenge of cloud removal in optical satellite images, by fusing with synthetic aperture radar (SAR) images. Recently, diffusion models have emerged as powerful tools for cloud…

Beyond general recognition tasks, specialized domains and fine-grained settings often encounter data scarcity, especially for tail classes. To obtain less biased and more reliable models under such scarcity, practitioners leverage diffusion…

We introduce CLARGA, a general-purpose multimodal fusion architecture for multimodal representation learning that works with any number and type of modalities without changing the underlying framework. Given a supervised dataset, CLARGA can…

Domain adaptation (DA) is transfer learning which aims to leverage labeled data in a related source domain to achieve informed knowledge transfer and help the classification of unlabeled data in a target domain. In this paper, we propose a…

We present a scalable framework designed to craft efficient lightweight models for video object detection utilizing self-training and knowledge distillation techniques. We scrutinize methodologies for the ideal selection of training images…

Data assimilation (DA) improves prediction of chaotic systems by combining model forecasts with sparse, noisy observations. Many DA methods are inherently probabilistic, but accurate probabilistic DA is often computationally expensive…

Text-to-video diffusion transformers encode semantic information unevenly across model depth, which constrains effective concept erasure. We identify a representational bottleneck, termed concept-layer topological alignment, under which…

Convolutional neural networks (CNNs) have been widely used in efficient image super-resolution. However, for CNN-based methods, performance gains often require deeper networks and larger feature maps, which increase complexity and inference…

Augmenting vision-language-action models (VLAs) with world models is promising for robotic policy learning but faces challenges in jointly predicting states and actions due to the modality gap. To address this, we propose DUal-STream…