Related papers: MLSA4Rec: Mamba Combined with Low-Rank Decomposed …

Recent deep models for image shadow removal often rely on attention-based architectures to capture long-range dependencies. However, their fixed attention patterns tend to mix illumination cues from irrelevant regions, leading to distorted…

Mamba is a newly proposed architecture which behaves like a recurrent neural network (RNN) with attention-like capabilities. These properties are promising for speaker diarization, as attention-based models have unsuitable memory…

Current multimodal sequential recommendation models are often unable to effectively explore and capture correlations among behavior sequences of users and items across different modalities, either neglecting correlations among sequence…

State-of-the-art sequential recommendation relies heavily on self-attention-based recommender models. Yet such models are computationally expensive and often too slow for real-time recommendation. Furthermore, the self-attention operation…

In this paper, we propose a novel sequence-aware recommendation model. Our model utilizes self-attention mechanism to infer the item-item relationship from user's historical interactions. With self-attention, it is able to estimate the…

Interactive conversational recommender systems have gained significant attention for their ability to capture user preferences through natural language interactions. However, existing approaches face substantial challenges in handling…

Sequential recommendation (SR) models often capture user preferences based on the historically interacted item IDs, which usually obtain sub-optimal performance when the interaction history is limited. Content-based sequential…

Recent deep sequential recommendation models often struggle to effectively model key characteristics of user behaviors, particularly in handling sequence length variations and capturing diverse interaction patterns. We propose STAR-Rec, a…

Multi-modal MRI offers valuable complementary information for diagnosis and treatment; however, its utility is limited by prolonged scanning times. To accelerate the acquisition process, a practical approach is to reconstruct images of the…

Conventional recommendation methods have achieved notable advancements by harnessing collaborative or sequential information from user behavior. Recently, large language models (LLMs) have gained prominence for their capabilities in…

Effective reasoning is crucial to solving complex mathematical problems. Recent large language models (LLMs) have boosted performance by scaling test-time computation through long chain-of-thought reasoning. However, transformer-based…

Recent 2D CNN-based domain adaptation approaches struggle with long-range dependencies due to limited receptive fields, making it difficult to adapt to target domains with significant spatial distribution changes. While transformer-based…

Sequential recommendation aims to recommend the next item of users' interest based on their historical interactions. Recently, the self-attention mechanism has been adapted for sequential recommendation, and demonstrated state-of-the-art…

Sequence models like Transformers and RNNs often overallocate attention to irrelevant context, leading to noisy intermediate representations. This degrades LLM capabilities by promoting hallucinations, weakening long-range and retrieval…

Sequential recommendation methods play a crucial role in modern recommender systems because of their ability to capture a user's dynamic interest from her/his historical interactions. Despite their success, we argue that these approaches…

Sequential recommender systems (SRS) could capture dynamic user preferences by modeling historical behaviors ordered in time. Despite effectiveness, focusing only on the \textit{collaborative signals} from behaviors does not fully grasp…

Recent advancements in imitation learning have been largely fueled by the integration of sequence models, which provide a structured flow of information to effectively mimic task behaviours. Currently, Decision Transformer (DT) and…

Cell detection in pathological images presents unique challenges due to densely packed objects, subtle inter-class differences, and severe background clutter. In this paper, we propose CellMamba, a lightweight and accurate one-stage…

The problem of Time-series Forecasting is generally addressed by recurrent, Transformer-based and the recently proposed Mamba-based architectures. However, existing architectures generally process their input at a single temporal scale,…

The increasing availability and diversity of multimodal data in recommender systems offer new avenues for enhancing recommendation accuracy and user satisfaction. However, these systems must contend with high-dimensional, sparse user-item…