Related papers: Multi-Source (Pre-)Training for Cross-Domain Measu…

Unsupervised domain adaptation (DA) has gained substantial interest in semantic segmentation. However, almost all prior arts assume concurrent access to both labeled source and unlabeled target, making them unsuitable for scenarios…

Recently unsupervised domain adaptation for the semantic segmentation task has become more and more popular due to high-cost of pixel-level annotation on real-world images. However, most domain adaptation methods are only restricted to…

Pretrained multilingual large language models have typically used heuristic temperature-based sampling to balance between different languages. However previous work has not systematically evaluated the efficacy of different pretraining…

Document-level neural machine translation has yielded attractive improvements. However, majority of existing methods roughly use all context sentences in a fixed scope. They neglect the fact that different source sentences need different…

Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval…

Inspired by the inductive transfer learning on computer vision, many efforts have been made to train contextualized language models that boost the performance of natural language processing tasks. These models are mostly trained on large…

Human perception and understanding is a major domain of computer vision which, like many other vision subdomains recently, stands to gain from the use of large models pre-trained on large datasets. We hypothesize that the most common…

Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where training data are collected from multiple sources, requiring multi-source domain…

Adapting visual object detectors to operational target domains is a challenging task, commonly achieved using unsupervised domain adaptation (UDA) methods. Recent studies have shown that when the labeled dataset comes from multiple source…

Definition modeling is an important task in advanced natural language applications such as understanding and conversation. Since its introduction, it focus on generating one definition for a target word or phrase in a given context, which…

Recent large language models support inputs of up to 10 million tokens, yet they perform poorly on long-context tasks that require complex reasoning. Such tasks can be solved using only a subset of the input -- a proxy context -- rather…

Recently, many pre-trained language models for source code have been proposed to model the context of code and serve as a basis for downstream code intelligence tasks such as code completion, code search, and code summarization. These…

Fine-tuning language models in a downstream task is the standard approach for many state-of-the-art methodologies in the field of NLP. However, when the distribution between the source task and target task drifts, \textit{e.g.},…

The field of natural language processing (NLP) has recently seen a large change towards using pre-trained language models for solving almost any task. Despite showing great improvements in benchmark datasets for various tasks, these models…

Broad textual understanding and in-context learning require language models that utilize full document contexts. Due to the implementation challenges associated with directly training long-context models, many methods have been proposed for…

To enhance the domain-specific capabilities of large language models, continued pre-training on a domain-specific corpus is a prevalent method. Recent work demonstrates that adapting models using reading comprehension data formatted by…

The performance of large language models (LLMs) is significantly affected by the quality and composition of their pre-training data, which is inherently diverse, spanning various languages, sources, and topics. Effectively integrating these…

Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) deal with all the samples from the two domains in a global or category-aware manner. They do…

Recent research has achieved impressive results on understanding and improving source code by building up on machine-learning techniques developed for natural languages. A significant advancement in natural-language understanding has come…

The Query Focused Text Summarization (QFTS) task aims at building systems that generate the summary of the text document(s) based on the given query. A key challenge in addressing this task is the lack of large labeled data for training the…