Search Results for author:
Found 25 papers, 6 papers with code
Impromptu Cybercrime Euphemism Detection
Moreover, we propose a detection framework tailored to this problem, which employs context augmentation modeling and multi-round iterative training.
Accelerating Vision Diffusion Transformers with Skip Branches
Diffusion Transformers (DiT), an emerging image and video generation model architecture, has demonstrated great potential because of its high generation quality and scalability properties.
Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models
Large Vision-Language Models (LVLMs) excel in cross-model tasks but experience performance declines in long-context reasoning due to overreliance on textual information and reduced visual dependency.
SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information
To address these challenges, we propose a self-refinement framework designed to teach LVLMs to Selectively Utilize Retrieved Information (SURf).
MemoryMamba: Memory-Augmented State Space Model for Defect Recognition
Existing vision models for defect recognition methods are insufficient for handling the complexities and variations of defects in contemporary manufacturing settings.
Streamlined Photoacoustic Image Processing with Foundation Models: A Training-Free Solution
Foundation models have rapidly evolved and have achieved significant accomplishments in computer vision tasks.
InsectMamba: Insect Pest Classification with State Space Model
The classification of insect pests is a critical task in agricultural technology, vital for ensuring food security and environmental sustainability.
Residual-based Language Models are Free Boosters for Biomedical Imaging
In this study, we uncover the unexpected efficacy of residual-based large language models (LLMs) as part of encoders for biomedical imaging tasks, a domain traditionally devoid of language or textual data.
MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
To overcome this challenge, we empirically study the reason why LLMs fail to resolve GitHub issues and analyze the major factors.
Visual In-Context Learning for Large Vision-Language Models
In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities.
KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation
However, previous methods are trained on the entire dataset without considering the fact that a portion of commit messages adhere to good practice (i. e., good-practice commits), while the rest do not.
Thread of Thought Unraveling Chaotic Contexts
Large Language Models (LLMs) have ushered in a transformative era in the field of natural language processing, excelling in tasks related to text comprehension and generation.
Multi-level, Forming Free, Bulk Switching Trilayer RRAM for Neuromorphic Computing at the Edge
To address all these challenges, we developed a forming-free and bulk switching RRAM technology based on a trilayer metal-oxide stack.
Style-Aware Contrastive Learning for Multi-Style Image Captioning
Existing multi-style image captioning methods show promising results in generating a caption with accurate visual content and desired linguistic style.
Multimodal Event Transformer for Image-guided Story Ending Generation
Specifically, we construct visual and semantic event graphs from story plots and ending image, and leverage event-based reasoning to reason and mine implicit information in a single modality.
Improving Cross-modal Alignment for Text-Guided Image Inpainting
Text-guided image inpainting (TGII) aims to restore missing regions based on a given text in a damaged image.
Fine-Grained Distillation for Long Document Retrieval
Long document retrieval aims to fetch query-relevant documents from a large-scale collection, where knowledge distillation has become de facto to improve a retriever by mimicking a heterogeneous yet powerful cross-encoder.
Disentangled and Robust Representation Learning for Bragging Classification in Social Media
Researching bragging behavior on social media arouses interest of computational (socio) linguists.
Unsupervised Knowledge Graph Construction and Event-centric Knowledge Infusion for Scientific NLI
Therefore, we propose an unsupervised knowledge graph construction method to build a scientific knowledge graph (SKG) without any labeled data.
ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models
In the data disambiguation stage, we employ the prompted GPT-3 model to understand possibly ambiguous triples from the input data and convert each into a short sentence with reduced ambiguity.
Towards Robust Ranker for Text Retrieval
A ranker plays an indispensable role in the de facto 'retrieval & rerank' pipeline, but its training still lags behind -- learning from moderate negatives or/and serving as an auxiliary module for a retriever.
ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification
Generating new events given context with correlated ones plays a crucial role in many event-centric reasoning tasks.
EventBERT: A Pre-Trained Model for Event Correlation Reasoning
Event correlation reasoning infers whether a natural language paragraph containing multiple events conforms to human common sense.
Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph
That is, we can only access training data in a high-resource language, while need to answer multilingual questions without any labeled data in target languages.
