Related papers: TransClean: Finding False Positives in Multi-Sourc…

Multiple object tracking (MOT) is the task containing detection and association. Plenty of trackers have achieved competitive performance. Unfortunately, for the lack of informative exchange on these subtasks, they are often biased toward…

Multilingual proficiency presents a significant challenge for large language models (LLMs). English-centric models are usually suboptimal in other languages, particularly those that are linguistically distant from English. This performance…

Despite the success of multimodal learning in cross-modal retrieval task, the remarkable progress relies on the correct correspondence among multimedia data. However, collecting such ideal data is expensive and time-consuming. In practice,…

There is a considerable body of work on data cleaning which employs various principles to rectify erroneous data and transform a dirty dataset into a cleaner one. One of prevalent approaches is probabilistic methods, including Bayesian…

Recent studies show that in supervised fine-tuning (SFT) of large language models (LLMs), data quality matters more than quantity. While most data cleaning methods concentrate on filtering entire samples, the quality of individual tokens…

The prevalence of noisy labels in real-world datasets poses a significant impediment to the effective deployment of deep learning models. While meta-learning strategies have emerged as a promising approach for addressing this challenge,…

This paper presents our system for SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval. In an era where misinformation spreads rapidly, effective fact-checking is increasingly critical. We introduce TriAligner, a…

Benchmark datasets in computer vision often contain off-topic images, near duplicates, and label errors, leading to inaccurate estimates of model performance. In this paper, we revisit the task of data cleaning and formalize it as either a…

Compressive learning (CL) is an emerging framework that integrates signal acquisition via compressed sensing (CS) and machine learning for inference tasks directly on a small number of measurements. It can be a promising alternative to…

Many robotics applications require alignment and fusion of observations obtained at multiple views to form a global model of the environment. Multi-way data association methods provide a mechanism to improve alignment accuracy of pairwise…

Generative models achieve remarkable results in multiple data domains, including images and texts, among other examples. Unfortunately, malicious users exploit synthetic media for spreading misinformation and disseminating deepfakes.…

Distantly Supervised Named Entity Recognition (DS-NER) has attracted attention due to its scalability and ability to automatically generate labeled data. However, distant annotation introduces many mislabeled instances, limiting its…

Cross-lingual Text Classification (CLC) consists of automatically classifying, according to a common set C of classes, documents each written in one of a set of languages L, and doing so more accurately than when naively classifying each…

Existing multilingual embedding models often encounter challenges in cross-lingual scenarios due to imbalanced linguistic resources and less consideration of cross-lingual alignment during training. Although standardized contrastive…

This paper presents TransRepair, a fully automatic approach for testing and repairing the consistency of machine translation systems. TransRepair combines mutation with metamorphic testing to detect inconsistency bugs (without access to…

Entity Matching (EM), which aims to identify all entity pairs referring to the same real-world entity from relational tables, is one of the most important tasks in real-world data management systems. Due to the labeling process of EM being…

The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and…

The rise of Large Language Models (LLMs) has reshaped machine translation (MT), but multilingual MT still relies heavily on parallel data for supervised fine-tuning (SFT), facing challenges like data scarcity for low-resource languages and…

Can we accurately identify the true correspondences from multimodal datasets containing mismatched data pairs? Existing methods primarily emphasize the similarity matching between the representations of objects across modalities,…

Weak supervision enables efficient development of training sets by reducing the need for ground truth labels. However, the techniques that make weak supervision attractive -- such as integrating any source of signal to estimate unknown…