Related papers: Multi-Granularity Guided Fusion-in-Decoder

Document Visual Question Answering (DocVQA) requires models to jointly understand textual semantics, spatial layout, and visual features. Current methods struggle with explicit spatial relationship modeling, inefficiency with…

The classification of indoor scenes is a critical component in various applications, such as intelligent robotics for assistive living. While deep learning has significantly advanced this field, models often suffer from reduced performance…

Open-ended text generation has become a prominent task in natural language processing due to the rise of powerful (large) language models. However, evaluating the quality of these models and the employed decoding strategies remains…

Transformer-based language models (LMs) pretrained on large text collections are proven to store a wealth of semantic knowledge. However, 1) they are not effective as sentence encoders when used off-the-shelf, and 2) thus typically lag…

The integration of Large Language Models (LLMs) into various applications has driven the need for structured and reliable responses. A key challenge in Retrieval-Augmented Generation (RAG) systems is ensuring that outputs align with…

Long-context multiple-choice question answering tasks require robust reasoning over extensive text sources. Since most of the pre-trained transformer models are restricted to processing only a few hundred words at a time, successful…

Large Vision-Language Models (LVLMs) have achieved impressive progress in multi-modal understanding and generation. However, they still tend to produce hallucinated content that is inconsistent with the visual input, which limits their…

Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective in improving the factual accuracy of large language models.…

Federated multi-view clustering has been proposed to mine the valuable information within multi-view data distributed across different devices and has achieved impressive results while preserving the privacy. Despite great progress, most…

Federated learning has been extensively studied and applied due to its ability to ensure data security in distributed environments while building better models. However, clients participating in federated learning still face limitations, as…

Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified modeling perspective, they often suffer from slow inference…

Open-ended text generation faces a critical challenge: balancing coherence with diversity in LLM outputs. While contrastive search-based decoding strategies have emerged to address this trade-off, their practical utility is often limited by…

The growing complexity of AI systems has intensified the need for transparency through Explainable AI (XAI). Counterfactual explanations (CFs) offer actionable "what-if" scenarios on three levels: Local CFs providing instance-specific…

Federated learning (FL) is a promising machine learning paradigm that collaborates with client models to capture global knowledge. However, deploying FL models in real-world scenarios remains unreliable due to the coexistence of…

Multi-source multi-hop question answering (QA) represents a challenging task in natural language processing due to the need for dynamic integration of heterogeneous knowledge sources and multi-step reasoning. Existing methods often suffer…

Complex degradations like noise, blur, and low resolution are typical challenges in real world image fusion tasks, limiting the performance and practicality of existing methods. End to end neural network based approaches are generally…

This paper addresses the problem of generating questions from a given context and an answer, specifically focusing on questions that require multi-hop reasoning across an extended context. Previous studies have suggested that key phrase…

Masked diffusion language models (MDLMs) enable parallel decoding by predicting all masked positions at each denoising step, yet existing training-free samplers usually decide which positions to commit at token-level granularity. We revisit…

3D semantic occupancy prediction is crucial for finely representing the surrounding environment, which is essential for ensuring the safety in autonomous driving. Existing fusion-based occupancy methods typically involve performing a…

Recent advancements in Large Language Models and Retrieval-Augmented Generation have boosted interest in domain-specific question-answering for enterprise products. However, AI Assistants often face challenges in multi-product QA settings,…