Related papers: Multi-range Reasoning for Machine Comprehension

Retrieval-Augmented Generation (RAG) mitigates hallucinations in Multimodal Large Language Models (MLLMs), yet existing systems struggle with complex cross-modal reasoning. Flat vector retrieval often ignores structural dependencies, while…

Scaling Low-Rank Adaptation (LoRA)-based Mixture-of-Experts (MoE) facilitates large language models (LLMs) to efficiently adapt to diverse tasks. However, traditional gating mechanisms that route inputs to the best experts may fundamentally…

In todays era huge volume of information exists everywhere. Therefore, it is very crucial to evaluate that information and extract useful, and often summarized, information out of it so that it may be used for relevant purposes. This…

Performing Retrieval-Augmented Generation (RAG) directly on mobile devices is promising for data privacy and responsiveness but is hindered by the architectural constraints of mobile NPUs. Specifically, current hardware struggles with the…

In various domains, Sequential Recommender Systems (SRS) have become essential due to their superior capability to discern intricate user preferences. Typically, SRS utilize transformer-based architectures to forecast the subsequent item…

Continual learning on edge platforms remains challenging because recurrent networks depend on energy-intensive training procedures and frequent data movement that are impractical for embedded deployments. This work introduces M2RU, a…

Multimodal retrieval over text corpora remains a fundamental challenge: the best vision-language encoder achieves only 27.6 nDCG@10 on MM-BRIGHT, a reasoning-intensive multimodal retrieval benchmark, underperforming strong text-only…

Objective: To develop a natural language processing system that solves both clinical concept extraction and relation extraction in a unified prompt-based machine reading comprehension (MRC) architecture with good generalizability for…

Recurrent Neural Networks (RNNs) are widely recognized for their proficiency in modeling temporal dependencies, making them highly prevalent in sequential data processing applications. Nevertheless, vanilla RNNs are confronted with the…

Considering deep sequence learning for practical application, two representative RNNs - LSTM and GRU may come to mind first. Nevertheless, is there no chance for other RNNs? Will there be a better RNN in the future? In this work, we propose…

Expressive representation of pose sequences is crucial for accurate motion modeling in human motion prediction (HMP). While recent deep learning-based methods have shown promise in learning motion representations, these methods tend to…

Knowledge-intensive visual question answering (VQA) requires external knowledge beyond image content, demanding precise visual grounding and coherent integration of visual and textual information. Although multimodal retrieval-augmented…

We present systematic efforts in building long-context multilingual text representation model (TRM) and reranker from scratch for text retrieval. We first introduce a text encoder (base size) enhanced with RoPE and unpadding, pre-trained in…

Magnetic Resonance Fingerprinting (MRF) enables fast quantitative imaging by matching signal evolutions to a predefined dictionary. However, conventional dictionary matching suffers from exponential growth in computational cost and memory…

Accurate multi-step port-of-call sequence prediction is vital for tactical resource orchestration and logistical efficiency. However, existing methods struggle with unreliable voyage schedules and the inability of AIS data to provide…

Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input text to the following predictor. However, rationalization…

Current visual grounding models are either based on a Multimodal Large Language Model (MLLM) that performs auto-regressive decoding, which is slow and risks hallucinations, or on re-aligning an LLM with vision features to learn new special…

Although large language models (LLM) have achieved remarkable performance, their enormous parameter counts hinder deployment on resource-constrained hardware. Low-rank compression can reduce both memory usage and computational demand, but…

While reasoning-augmented large language models (RLLMs) significantly enhance complex task performance through extended reasoning chains, they inevitably introduce substantial unnecessary token consumption, particularly for simpler problems…

Multimodal content, such as mixing text with images, presents significant challenges to rumor detection in social media. Existing multimodal rumor detection has focused on mixing tokens among spatial and sequential locations for unimodal…