Related papers: BoundRL: Efficient Structured Text Segmentation th…

Natural generation allows Large Language Models (LLMs) to produce free-form responses with rich reasoning, yet the lack of structure makes outputs difficult to verify. Conversely, constrained decoding ensures standardized formats but can…

Large Reasoning Models (LRMs) achieve strong reasoning performance by generating long chains of thought (CoTs), yet only a small fraction of these traces meaningfully contributes to answer prediction, while the majority contains repetitive…

Unsupervised automatic speech recognition (ASR) aims to learn the mapping between the speech signal and its corresponding textual transcription without the supervision of paired speech-text data. A word/phoneme in the speech signal is…

We present a new Convolutional Neural Network (CNN) model for text classification that jointly exploits labels on documents and their component sentences. Specifically, we consider scenarios in which annotators explicitly mark sentences (or…

There is a growing interest in expanding the input capacity of language models (LMs) across various domains. However, simply increasing the context window does not guarantee robust performance across diverse long-input processing tasks,…

Unsupervised methods are widely used to induce latent semantic structure from large text collections, yet their outputs often contain incoherent, redundant, or poorly grounded clusters that are difficult to validate without labeled data. We…

A wide range of control perspectives have been explored in controllable text generation. Structure-controlled summarization is recently proposed as a useful and interesting research direction. However, current structure-controlling methods…

Constrained text generation remains a challenging task, particularly when dealing with hard constraints. Traditional NLP approaches prioritize generating meaningful and coherent output. Also, the current state-of-the-art methods often lack…

In this paper, we propose a Boundary-aware Graph Reasoning (BGR) module to learn long-range contextual features for semantic segmentation. Rather than directly construct the graph based on the backbone features, our BGR module explores a…

Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs), especially when structured reference answers are…

Reinforcement Learning (RL) has proven highly effective in aligning Large Language Models (LLMs) with human preferences. Typical RL methods optimize under an overall sequence reward, which can lead to a suboptimal learning process. This…

Despite rapid advancements in the capabilities of generative models, pretrained text-to-image models still struggle in capturing the semantics conveyed by complex prompts that compound multiple objects and instance-level attributes.…

Recently, segmentation-based methods are quite popular in scene text detection, which mainly contain two steps: text kernel segmentation and expansion. However, the segmentation process only considers each pixel independently, and the…

As Large Language Models (LLMs) become integral to software development workflows, their ability to generate structured outputs has become critically important. We introduce StructEval, a comprehensive benchmark for evaluating LLMs'…

Effective personalization on large-scale job platforms requires modeling members based on heterogeneous textual sources, including profiles, professional data, and search activity logs. As recommender systems increasingly adopt Large…

Recent advances in product bundling have leveraged multimodal information through sophisticated encoders, but remain constrained by limited semantic understanding and a narrow scope of knowledge. Therefore, some attempts employ In-context…

Tokenization is a hardcoded compression step which remains in the training pipeline of Large Language Models (LLMs), despite a general trend towards architectures becoming increasingly end-to-end. Prior work has shown promising results at…

Enlarging the context window of large language models (LLMs) has become a crucial research area, particularly for applications involving extremely long texts. In this work, we propose a novel training-free framework for processing long…

Fine-grained visual categorization is to recognize hundreds of subcategories belonging to the same basic-level category, which is a highly challenging task due to the quite subtle and local visual distinctions among similar subcategories.…

Legal documents are unstructured, use legal jargon, and have considerable length, making them difficult to process automatically via conventional text processing techniques. A legal document processing system would benefit substantially if…