Related papers: RFiD: Towards Rational Fusion-in-Decoder for Open-…

Accurate air quality prediction is essential for public health, environmental monitoring, and industrial safety. However, most existing approaches rely on centralized learning paradigms, which introduce challenges related to scalability,…

Federated learning (FL) is a distributed learning paradigm that maximizes the potential of data-driven models for edge devices without sharing their raw data. However, devices often have non-independent and identically distributed (non-IID)…

Diffusion language models enable parallel token generation through block-wise decoding, but their irreversible commitments can lead to stagnation, where the reverse diffusion process fails to make further progress under a suboptimal…

Existing synthetic datasets (FigureQA, DVQA) for reasoning over plots do not contain variability in data labels, real-valued data, or complex reasoning questions. Consequently, proposed models for these datasets do not fully address the…

Naturalistic fMRI encoding must handle multimodal inputs, shifting fusion styles, and pronounced inter-subject variability. We introduce AFIRE (Agnostic Framework for Multimodal fMRI Response Encoding), an agnostic interface that…

This paper presents an advancement in Question-Answering (QA) systems using a Retrieval Augmented Generation (RAG) framework to enhance information extraction from PDF files. Recognizing the richness and diversity of data within…

Visual question answering (VQA) has recently been introduced to remote sensing to make information extraction from overhead imagery more accessible to everyone. VQA considers a question (in natural language, therefore easy to formulate)…

Recent advances in Deep Learning (DL) have boosted data-driven System Identification (SysID), but reliable use requires Uncertainty Quantification (UQ) alongside accurate predictions. Although UQ-capable models such as Fuzzy ODE (FODE) can…

Federated Learning (FL) offers a framework for training models collaboratively while preserving data privacy of each client. Recently, research has focused on Federated Source-Free Domain Adaptation (FFREEDA), a more realistic scenario…

Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial…

Some Natural Language Generation (NLG) tasks require both faithfulness and diversity. The decoding strategy is intensively related to the quality of the generated text. Strategies such as beam search, greedy search, etc., perform with low…

Entity disambiguation (ED), which links the mentions of ambiguous entities to their referent entities in a knowledge base, serves as a core component in entity linking (EL). Existing generative approaches demonstrate improved accuracy…

Generative retrieval (GR) reframes document retrieval as an end-to-end task of generating sequential document identifiers (DocIDs). Existing GR methods predominantly rely on left-to-right auto-regressive decoding, which suffers from two…

Question answering (QA) is a high-level ability of natural language processing. Most extractive ma-chine reading comprehension models focus on factoid questions (e.g., who, when, where) and restrict the output answer as a short and…

Medical Visual Question Answering (MedVQA) aims to generate clinically reliable answers conditioned on complex medical images and questions. However, existing methods often overfit to superficial cross-modal correlations, neglecting the…

Visual Question Answering is a multi-modal task that aims to measure high-level visual understanding. Contemporary VQA models are restrictive in the sense that answers are obtained via classification over a limited vocabulary (in the case…

Multimodal learning faces a fundamental tension between deep, fine-grained fusion and computational scalability. While cross-attention models achieve strong performance through exhaustive pairwise fusion, their quadratic complexity is…

Retrieval-based augmentations (RA) incorporating knowledge from an external database into language models have greatly succeeded in various knowledge-intensive (KI) tasks. However, integrating retrievals in non-knowledge-intensive (NKI)…

Visual question answering (VQA) refers to the problem where, given an image and a natural language question about the image, a correct natural language answer has to be generated. A VQA model has to demonstrate both the visual understanding…

With the rapid development of imaging sensor technology in the field of remote sensing, multi-modal remote sensing data fusion has emerged as a crucial research direction for land cover classification tasks. While diffusion models have made…