Related papers: From Events to Trending: A Multi-Stage Hotspots De…
Recently, open domain multi-turn chatbots have attracted much interest from lots of researchers in both academia and industry. The dominant retrieval-based methods use context-response matching mechanisms for multi-turn response selection.…
Traditional approaches to safety event analysis in autonomous systems have relied on complex machine learning models and extensive datasets for high accuracy and reliability. However, the advent of Multimodal Large Language Models (MLLMs)…
Answering numerical questions over hybrid contents from the given tables and text(TextTableQA) is a challenging task. Recently, Large Language Models (LLMs) have gained significant attention in the NLP community. With the emergence of large…
Generic event boundary detection is an important yet challenging task in video understanding, which aims at detecting the moments where humans naturally perceive event boundaries. The main challenge of this task is perceiving various…
As a cornerstone of modern information access, search engines have become indispensable in everyday life. With the rapid advancements in AI and natural language processing (NLP) technologies, particularly large language models (LLMs),…
Crowding at the entrances of large events may lead to critical and life-threatening situations, particularly when people start pushing each other to reach the event faster. Automatic and timely identification of pushing behavior would help…
Detecting anomalies in discrete event logs is critical for ensuring system reliability, security, and efficiency. Traditional window-based methods for log anomaly detection often suffer from context bias and fuzzy localization, which hinder…
Detecting video moments and highlights from natural-language queries have been unified by transformer-based methods. Other works use generative Multimodal LLM (MLLM) to predict moments and/or highlights as text timestamps, utilizing its…
We present a novel method for hierarchical topic detection where topics are obtained by clustering documents in multiple ways. Specifically, we model document collections using a class of graphical models called hierarchical latent tree…
Process data, temporally ordered categorical observations, are of recent interest due to its increasing abundance and the desire to extract useful information. A process is a collection of time-stamped events of different types, recording…
Social networks enable users to freely communicate with each other and share their recent news, ongoing activities or views about different topics. As a result, they can be seen as a potentially viable source of information to understand…
We study a problem of detecting priming events based on a time series index and an evolving document stream. We define a priming event as an event which triggers abnormal movements of the time series index, i.e., the Iraq war with respect…
The exponential growth of user-generated content on social media platforms has precipitated significant challenges in information management, particularly in content organization, retrieval, and discovery. Hashtags, as a fundamental…
Large Language Models (LLMs) have gained significant attention but also raised concerns due to the risk of misuse. Jailbreak prompts, a popular type of adversarial attack towards LLMs, have appeared and constantly evolved to breach the…
Detection of emerging topics are now receiving renewed interest motivated by the rapid growth of social networks. Conventional term-frequency-based approaches may not be appropriate in this context, because the information exchanged are not…
As the development of academic conferences fosters global scholarly communication, researchers consistently need to obtain accurate and up-to-date information about academic conferences. Since the information is scattered, using an…
Retrieval augmentation is critical when Language Models (LMs) exploit non-parametric knowledge related to the query through external knowledge bases before reasoning. The retrieved information is incorporated into LMs as context alongside…
Retrieval-Augmented Generation (RAG) couples a retriever with a large language model (LLM) to ground generated responses in external evidence. While this framework enhances factuality and domain adaptability, it faces a key bottleneck:…
Retrieval augmented generation has emerged as an effective method to enhance large language model performance. This approach typically relies on an internal retrieval module that uses various indexing mechanisms to manage a static…
The rapid advancement of talking-head deepfake generation fueled by advanced generative models has elevated the realism of synthetic videos to a level that poses substantial risks in domains such as media, politics, and finance. However,…