Related papers: Concept Relation Discovery and Innovation Enabling…
Although foundation models (FMs) claim to be powerful, their generalization ability significantly decreases when faced with distribution shifts, weak supervision, or malicious attacks in the open world. On the other hand, most domain…
The vast growth of data has rendered traditional manual inspection infeasible, necessitating the adoption of computational methods for efficient data exploration. Topic modeling has emerged as a powerful tool for analyzing large-scale…
Open-vocabulary object detection (OVOD) enables novel category detection via vision-language alignment, but massive model sizes hinder deployment on resource-constrained devices. While quantization offers practical compression, we reveal…
Conceptual combination is a cognitive process that merges basic concepts, enabling the creation of complex expressions. During this process, the properties of combination (e.g., the whiteness of a peeled apple) can be inherited from basic…
Concept Bottleneck Models (CBMs) enable interpretable image classification by structuring predictions around human-understandable concepts, but extending this paradigm to video remains challenging due to the difficulty of extracting…
We introduce Co-DETECT (Collaborative Discovery of Edge cases in TExt ClassificaTion), a novel mixed-initiative annotation framework that integrates human expertise with automatic annotation guided by large language models (LLMs). Co-DETECT…
Dataset distillation (DD) has witnessed significant progress in creating small datasets that encapsulate rich information from large original ones. Particularly, methods based on generative priors show promising performance, while…
Emotion recognition is a crucial task for human conversation understanding. It becomes more challenging with the notion of multimodal data, e.g., language, voice, and facial expressions. As a typical solution, the global- and the local…
We proposed a novel multilayer correlated topic model (MCTM) to analyze how the main ideas inherit and vary between a document and its different segments, which helps understand an article's structure. The variational…
Large language models (LLMs) demonstrate remarkable text comprehension and generation capabilities but often lack the ability to utilize up-to-date or domain-specific knowledge not included in their training data. To address this gap, we…
We propose a new problem called coordinated topic modeling that imitates human behavior while describing a text corpus. It considers a set of well-defined topics like the axes of a semantic space with a reference representation. It then…
This paper describes a new kind of knowledge representation and mining system which we are calling the Semantic Knowledge Graph. At its heart, the Semantic Knowledge Graph leverages an inverted index, along with a complementary uninverted…
In this paper, we propose a new system called ASET that allows users to perform structured explorations of text collections in an ad-hoc manner. The main idea of ASET is to use a new two-phase approach that first extracts a superset of…
Many recent language models (LMs) are capable of in-context learning (ICL), manifested in the LMs' ability to perform a new task solely from natural-language instruction. Previous work curating in-context learners assumes that ICL emerges…
Contextual information has been shown to be powerful for semantic segmentation. This work proposes a novel Context-based Tandem Network (CTNet) by interactively exploring the spatial contextual information and the channel contextual…
Extracting structured knowledge from unstructured data still faces practical limitations: entity and event extraction pipelines remain brittle, knowledge graph construction requires costly ontology engineering, and cross-domain…
The knowledge graph(KG) composed of entities with their descriptions and attributes, and relationship between entities, is finding more and more application scenarios in various natural language processing tasks. In a typical knowledge…
Topic taxonomies, which represent the latent topic (or category) structure of document collections, provide valuable knowledge of contents in many applications such as web search and information filtering. Recently, several unsupervised…
This paper presents the AToMiC (Authoring Tools for Multimedia Content) dataset, designed to advance research in image/text cross-modal retrieval. While vision-language pretrained transformers have led to significant improvements in…
Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object detection. In this work, we address this…