Related papers: CAT: Contrastive Adapter Training for Personalized…

Conditional image generation is the task of generating diverse images using class label information. Although many conditional Generative Adversarial Networks (GAN) have shown realistic results, such methods consider pairwise relations…

We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, with different data…

User modeling, which aims to capture users' characteristics or interests, heavily relies on task-specific labeled data and suffers from the data sparsity issue. Several recent studies tackled this problem by pre-training the user model on…

Fine-tuning large-scale pre-trained models is prohibitively expensive in terms of computation and memory costs. Low-Rank Adaptation (LoRA), a popular Parameter-Efficient Fine-Tuning (PEFT) method, offers an efficient solution by optimizing…

Recent advances in text-to-image customization have enabled high-fidelity, context-rich generation of personalized images, allowing specific concepts to appear in a variety of scenarios. However, current methods struggle with combining…

Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual representations. It uses pairs of augmentations of unlabeled training examples to define a classification task for pretext learning of a deep…

Pre-trained language models (PLMs) have achieved remarkable success on various natural language understanding tasks. Simple fine-tuning of PLMs, on the other hand, might be suboptimal for domain-specific tasks because they cannot possibly…

In response to an object presentation, supervised learning schemes generally respond with a parsimonious label. Upon a similar presentation we humans respond again with a label, but are flooded, in addition, by a myriad of associations. A…

We explore the "hidden" ability of large-scale pre-trained image generation models, such as Stable Diffusion and Imagen, in non-visible light domains, taking Synthetic Aperture Radar (SAR) data for a case study. Due to the inherent…

Cost aggregation is a highly important process in image matching tasks, which aims to disambiguate the noisy matching scores. Existing methods generally tackle this by hand-crafted or CNN-based methods, which either lack robustness to…

Commit Classification (CC) is an important task in software maintenance, which helps software developers classify code changes into different types according to their nature and purpose. It allows developers to understand better how their…

Continual learning in Neural Machine Translation (NMT) faces the dual challenges of catastrophic forgetting and the high computational cost of retraining. This study establishes Low-Rank Adaptation (LoRA) as a parameter-efficient framework…

Class imbalance is a persistent challenge in visual recognition, particularly in safety-critical domains where collecting positive examples is expensive and rare events are inherently underrepresented. We propose a lightweight synthetic…

Bootstrap-based Self-Supervised Learning (SSL) has achieved remarkable progress in audio understanding. However, existing methods typically operate at a single level of granularity, limiting their ability to model the diverse temporal and…

Low-Rank Adaptation (LoRA) is a popular technique for parameter-efficient fine-tuning of Large Language Models (LLMs). We study how different LoRA modules can be merged to achieve skill composition -- testing the performance of the merged…

Despite the huge progress in myriad generation tasks, pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts with maximization-based decoding algorithms for open-ended generation. We attribute their…

We revisit continual learning~(CL), which enables pre-trained vision transformers (ViTs) to sequentially fine-tune on new downstream tasks over time. However, as the scale of these models increases, catastrophic forgetting remains a more…

Vision-language foundation models have been incredibly successful in a wide range of downstream computer vision tasks using adaptation methods. However, due to the high cost of obtaining pre-training datasets, pairs with weak image-text…

In recent years, the field of image generation has witnessed significant advancements, particularly in fine-tuning methods that align models with universal human preferences. This paper explores the critical role of preference data in the…

Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances established during pre-training can be interpreted as strong…