Related papers: Learning to Generate Cross-Task Unexploitable Exam…

The recent advancements in generative language models have demonstrated their ability to memorize knowledge from documents and recall knowledge to respond to user queries effectively. Building upon this capability, we propose to enable…

Our goal in this research is to study a more realistic environment in which we can conduct weakly-supervised multi-modal instance-level product retrieval for fine-grained product categories. We first contribute the Product1M datasets, and…

Image extrapolation aims at expanding the narrow field of view of a given image patch. Existing models mainly deal with natural scene images of homogeneous regions and have no control of the content generation process. In this work, we…

Inspired by the software industry's practice of offering different editions or versions of a product tailored to specific user groups or use cases, we propose a novel task, namely, training-free editioning, for text-to-image models.…

Unlike static and rigid user interfaces, generative and malleable user interfaces offer the potential to respond to diverse users' goals and tasks. However, current approaches primarily rely on generating code, making it difficult for…

Pre-trained video models learn powerful priors for generating high-quality, temporally coherent content. While these models excel at temporal coherence, their dynamics are often constrained by the continuous nature of their training data.…

A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we learn an optimal model in training data, it could have better generalization performance in testing tasks. However, learning such a…

Generative image models, since introduction, have become a global phenomenon. From new arts becoming possible to new vectors of abuse, many new capabilities have become available. One of the challenging issues with generative models is…

Controllable Text Generation (CTG) has obtained great success due to its fine-grained generation ability obtained by focusing on multiple attributes. However, most existing CTG researches overlook how to utilize the attribute entanglement…

Unsupervised domain adaptation generalizes neural retrievers to an unseen domain by generating pseudo queries on target domain documents. The quality and efficiency of this adaptation critically depend on which documents are selected for…

Model-based deep reinforcement learning has achieved success in various domains that require high sample efficiencies, such as Go and robotics. However, there are some remaining issues, such as planning efficient explorations to learn more…

Leveraging datasets available to learn a model with high generalization ability to unseen domains is important for computer vision, especially when the unseen domain's annotated data are unavailable. We study a novel and practical problem…

Online reviews provide rich information about products and service, while it remains inefficient for potential consumers to exploit the reviews for fulfilling their specific information need. We propose to explore question generation as a…

With the rapid development of deep learning methods, there have been many breakthroughs in the field of text classification. Models developed for this task have been shown to achieve high accuracy. However, most of these models are trained…

Generative models typically sample outputs independently, and recent inference-time guidance and scaling algorithms focus on improving the quality of individual samples. However, in real-world applications, users are often presented with a…

Text-based person retrieval aims to identify specific individuals within an image database using textual descriptions. Due to the high cost of annotation and privacy protection, researchers resort to synthesized data for the paradigm of…

We propose a novel approach for using unsupervised boosting to create an ensemble of generative models, where models are trained in sequence to correct earlier mistakes. Our meta-algorithmic framework can leverage any existing base learner…

Knowledge-intensive language tasks (KILTs) benefit from retrieving high-quality relevant contexts from large external knowledge corpora. Learning task-specific retrievers that return relevant contexts at an appropriate level of semantic…

This paper addresses a crucial challenge in retrieval-augmented generation-based relation extractors; the end-to-end training is not applicable to conventional retrieval-augmented generation due to the non-differentiable nature of instance…

Over the past decades, researchers and ML practitioners have come up with better and better ways to build, understand and improve the quality of ML models, but mostly under the key assumption that the training data is distributed…