Related papers: Label-Efficient Model Selection for Text Generatio…
Aligning diffusion models with user preferences has been a key challenge. Existing methods for aligning diffusion models either require retraining or are limited to differentiable reward functions. To address these limitations, we propose a…
Text-to-image generation using diffusion models has gained increasing popularity due to their ability to produce high-quality, realistic images based on text prompts. However, efficiently serving these models is challenging due to their…
Diffusion Models have shown remarkable proficiency in image and video synthesis. As model size and latency increase limit user experience, hybrid edge-cloud collaborative framework was recently proposed to realize fast inference and…
Learning from noisy labels is a challenge that arises in many real-world applications where training data can contain incorrect or corrupted labels. When fine-tuning language models with noisy labels, models can easily overfit the label…
Annotating large collections of textual data can be time consuming and expensive. That is why the ability to train models with limited annotation budgets is of great importance. In this context, it has been shown that under tight annotation…
Human evaluation is increasingly critical for assessing large language models, capturing linguistic nuances, and reflecting user preferences more accurately than traditional automated metrics. However, the resource-intensive nature of this…
A major challenge in Natural Language Processing is obtaining annotated data for supervised learning. An option is the use of crowdsourcing platforms for data annotation. However, crowdsourcing introduces issues related to the annotator's…
While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which addresses both families of tasks simultaneously. We…
We present a supervised learning framework of training generative models for density estimation. Generative models, including generative adversarial networks, normalizing flows, variational auto-encoders, are usually considered as…
Creating large-scale datasets for training high-performance generative models is often prohibitively expensive, especially when associated attributes or annotations must be provided. As a result, merging existing datasets has become a…
We propose a novel sample selection method for image classification in the presence of noisy labels. Existing methods typically consider small-loss samples as correctly labeled. However, some correctly labeled samples are inherently…
Automated object detection has become increasingly valuable across diverse applications, yet efficient, high-quality annotation remains a persistent challenge. In this paper, we present the development and evaluation of a platform designed…
We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The…
Score-based models generate samples by mapping noise to data (and vice versa) via a high-dimensional diffusion process. We question whether it is necessary to run this entire process at high dimensionality and incur all the inconveniences…
While generative models produce high-quality images of concepts learned from a large-scale database, a user often wishes to synthesize instantiations of their own concepts (for example, their family, pets, or items). Can we teach a model to…
Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models, as they can be…
Evaluating modern machine learning models has become prohibitively expensive. Benchmarks such as LMMs-Eval and HELM demand thousands of GPU hours per model. Costly evaluation reduces inclusivity, slows the cycle of innovation, and worsens…
Diffusion models have achieved remarkable success in generating high-fidelity content but suffer from slow, iterative sampling, resulting in high latency that limits their use in interactive applications. We introduce DRiffusion, a parallel…
Discrete diffusion models have recently shown significant progress in modeling complex data, such as natural languages and DNA sequences. However, unlike diffusion models for continuous data, which can generate high-quality samples in just…
Data-driven deep learning models have enabled tremendous progress in change detection (CD) with the support of pixel-level annotations. However, collecting diverse data and manually annotating them is costly, laborious, and…