Related papers: Visual Word Selection without Re-Coding and Re-Poo…

Explicit concept space models have proven efficacy for text representation in many natural language and text mining applications. The idea is to embed textual structures into a semantic space of concepts which captures the main ideas,…

Distributed word representation (a.k.a. word embedding) is a key focus in natural language processing (NLP). As a highly successful word embedding model, Word2Vec offers an efficient method for learning distributed word representations on…

CLIP (Contrastive Language-Image Pretraining) has become a popular choice for various downstream tasks. However, recent studies have questioned its ability to represent compositional concepts effectively. These works suggest that CLIP often…

Open world image segmentation aims to achieve precise segmentation and semantic understanding of targets within images by addressing the infinitely open set of object categories encountered in the real world. However, traditional closed-set…

Subword segmentation is widely used to address the open vocabulary problem in machine translation. The dominant approach to subword segmentation is Byte Pair Encoding (BPE), which keeps the most frequent words intact while splitting the…

Vision Transformers (ViTs) have emerged as the backbone of many segmentation models, consistently achieving state-of-the-art (SOTA) performance. However, their success comes at a significant computational cost. Image token pruning is one of…

Text-to-image retrieval is a fundamental task in vision-language learning, yet in real-world scenarios it is often challenged by short and underspecified user queries. Such queries are typically only one or two words long, rendering them…

Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs…

To interpret deep models' predictions, attention-based visual cues are widely used in addressing \textit{why} deep models make such predictions. Beyond that, the current research community becomes more interested in reasoning \textit{how}…

Recent advances in segmentation-free keyword spotting treat this problem w.r.t. an object detection paradigm and borrow from state-of-the-art detection systems to simultaneously propose a word bounding box proposal mechanism and compute a…

Predicting program behavior and reasoning about code execution remain significant challenges in software engineering, particularly for large language models (LLMs) designed for code analysis. While these models excel at understanding static…

With the rapid development in deep learning, deep neural networks have been widely adopted in many real-life natural language applications. Under deep neural networks, a pre-defined vocabulary is required to vectorize text inputs. The…

Chain-of-thought (CoT) reasoning greatly improves the interpretability and problem-solving abilities of multimodal large language models (MLLMs). However, existing approaches are focused on text CoT, limiting their ability to leverage…

The established redundancy in visual tokens within large vision-language models allows pruning to effectively reduce their substantial computational demands. Previous methods typically employ heuristic layer-specific pruning strategies…

Explainability is a longstanding challenge in deep learning, especially in high-stakes domains like healthcare. Common explainability methods highlight image regions that drive an AI model's decision. Humans, however, heavily rely on…

Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce…

Open-vocabulary keyword spotting (OV-KWS) enables personalized device control via arbitrary voice commands. Recently, researchers have explored using audio-text joint embeddings, allowing users to enroll phrases with text, and proposed…

This paper presents the first study aimed at capturing stylistic similarity between words in an unsupervised manner. We propose extending the continuous bag of words (CBOW) model (Mikolov et al., 2013) to learn style-sensitive word vectors…

To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sliding window to concatenate spatially adjacent visual tokens.…

Vision tokens in multimodal large language models often dominate huge computational overhead due to their excessive length compared to linguistic modality. Abundant recent methods aim to solve this problem with token pruning, which first…