Related papers: Stack Trace-Based Crash Deduplication with Transfo…

Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. However, the domain gap between synthetic and real images poses a challenge in acquiring feature representations…

The \textit{de facto} paradigm for applying dense retrieval (DR) to new tasks involves fine-tuning a pre-trained model for a specific task. However, this paradigm has two significant limitations: (1) It is difficult adapt the DR to a new…

Crash localization, an important step in debugging crashes, is challenging when dealing with an extremely large number of diverse applications and platforms and underlying root causes. Large-scale error reporting systems, e.g., Windows…

Automated detection of software vulnerabilities is critical for enhancing security, yet existing methods often struggle with the complexity and diversity of modern codebases. In this paper, we introduce EnStack, a novel ensemble stacking…

Accurate trajectory prediction is a cornerstone for the safe operation of autonomous driving systems, where understanding the dynamic behavior of surrounding agents is crucial. Transformer-based architectures have demonstrated significant…

Handwriting recognition is a challenging and critical problem in the fields of pattern recognition and machine learning, with applications spanning a wide range of domains. In this paper, we focus on the specific issue of recognizing…

In this paper, we propose Stacked DeBERT, short for Stacked Denoising Bidirectional Encoder Representations from Transformers. This novel model improves robustness in incomplete data, when compared to existing systems, by designing a novel…

Prompt Tuning (PT) enables the adaptation of Pre-trained Large Language Models (PLMs) to downstream tasks by optimizing a small amount of soft virtual tokens, which are prepended to the input token embeddings. Recently, Decomposed Prompt…

Traditional automated crash analysis systems heavily rely on static statistical models and historical data, requiring significant manual interpretation and lacking real-time predictive capabilities. This research presents an innovative…

Adapting Large Multimodal Models (LMMs) to real-world scenarios poses the dual challenges of learning from sequential data streams while handling frequent modality incompleteness, a task known as Continual Missing Modality Learning (CMML).…

DEtection TRansformer (DETR) and its variants (DETRs) have been successfully applied to crowded pedestrian detection, which achieved promising performance. However, we find that, in different degrees of crowded scenes, the number of DETRs'…

Effective document reranking is essential for improving search relevance across diverse applications. While Large Language Models (LLMs) excel at reranking due to their deep semantic understanding and reasoning, their high computational…

The Detection Transformer (DETR), by incorporating the Hungarian algorithm, has significantly simplified the matching process in object detection tasks. This algorithm facilitates optimal one-to-one matching of predicted bounding boxes to…

Current multi-modal object re-identification approaches based on large-scale pre-trained backbones (i.e., ViT) have displayed remarkable progress and achieved excellent performance. However, these methods usually adopt the standard full…

The integration of extensive, dynamic knowledge into Large Language Models (LLMs) remains a significant challenge due to the inherent entanglement of factual data and reasoning patterns. Existing solutions, ranging from non-parametric…

Deep learning and big data algorithms have become widely used in industrial applications to optimize several tasks in many complex systems. Particularly, deep learning model for diagnosing and prognosing machinery health has leveraged…

Traditional clustering methods often perform clustering with low-level indiscriminative representations and ignore relationships between patterns, resulting in slight achievements in the era of deep learning. To handle this problem, we…

Textual adapter-based tuning methods have shown significant potential in transferring knowledge from pre-trained Vision-Language Models (VLMs) to downstream tasks. Existing works generally employ the deterministic textual feature adapter to…

Diffusion Language Models (DLMs) generate text by iteratively denoising masked token sequences, offering a tradeoff between parallelism and quality compared to autoregressive models. In current practice, the number of tokens decoded per…

Decentralized stochastic optimization has emerged as a fundamental paradigm for large-scale machine learning. However, practical implementations often rely on biased gradient estimators arising from communication compression or inexact…