Related papers: H-Net++: Hierarchical Dynamic Chunking for Tokeniz…

The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations: (1) their optimal depth is apriori unknown, requiring…

Neural network training is a memory- and compute-intensive task. Quantization, which enables low-bitwidth formats in training, can significantly mitigate the workload. To reduce quantization error, recent methods have developed new data…

Scene text spotting is of great importance to the computer vision community due to its wide variety of applications. Recent methods attempt to introduce linguistic knowledge for challenging recognition rather than pure visual…

Recent advancements in large language models (LLMs) have remarkably enhanced performances on a variety of tasks in multiple languages. However, tokenizers in LLMs trained primarily on English-centric corpora often overly fragment a text…

Recently, the hybrid convolutional neural network hidden Markov model (CNN-HMM) has been introduced for offline handwritten Chinese text recognition (HCTR) and has achieved state-of-the-art performance. However, modeling each of the large…

Recurrent neural network (RNN) based character-level language models (CLMs) are extremely useful for modeling out-of-vocabulary words by nature. However, their performance is generally much worse than the word-level language models (WLMs),…

Semantic segmentation is a pixel-level prediction task to classify each pixel of the input image. Deep learning models, such as convolutional neural networks (CNNs), have been extremely successful in achieving excellent performances in this…

This paper summarizes the work done by the authors for the Zero Resource Speech Challenge organized in the technical program of Interspeech 2015. The goal of the challenge is to discover linguistic units directly from unlabeled speech data.…

Recent large language models have shifted SVG generation from differentiable rendering optimization to autoregressive program synthesis. However, existing approaches still rely on generic byte-level tokenization inherited from natural…

Large-scale pre-trained Vision-Language Models (VLMs) have significantly advanced transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, undermining their ability to…

As deep neural networks (DNNs) grow in complexity and size, the resultant increase in communication overhead during distributed training has become a significant bottleneck, challenging the scalability of distributed training systems.…

Recently, large language models (LLMs) have demonstrated superior performance across various tasks by adhering to scaling laws, which significantly increase model size. However, the huge computation overhead during inference hinders the…

Diffusion models have revolutionized generative tasks, especially in the domain of text-to-image synthesis; however, their iterative denoising process demands substantial computational resources. In this paper, we present a novel…

The organization of latent token representations plays a crucial role in determining the stability, generalization, and contextual consistency of language models, yet conventional approaches to embedding refinement often rely on parameter…

High-quality main content extraction from web pages is a critical prerequisite for constructing large-scale training corpora. While traditional heuristic extractors are efficient, they lack the semantic reasoning required to handle the…

Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image…

Words are properly segmented in the Persian writing system; in practice, however, these writing rules are often neglected, resulting in single words being written disjointedly and multiple words written without any white spaces between…

Speech, Music and Noise classification/segmentation is an important preprocessing step for audio processing/indexing. To this end, we propose a novel 1D Convolutional Neural Network (CNN) - SwishNet. It is a fast and lightweight…

In-Context Learning and Chain-of-Thought prompting improve reasoning in large language models (LLMs). These typically come at the cost of longer, more expensive prompts that may contain redundant information. Prompt compression based on…

Hierarchical and complex Mathematical Expression Recognition (MER) is challenging due to multiple possible interpretations of a formula, complicating both parsing and evaluation. In this paper, we introduce the Hierarchical Detail-Focused…