Related papers: Anchored Alignment: Preventing Positional Collapse…

Multimodal recommendation has emerged as a mainstream paradigm, typically leveraging text and visual embeddings extracted from pre-trained models such as Sentence-BERT, Vision Transformers, and ResNet. This approach is founded on the…

Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language alignment, yet they remain limited in visual-spatial reasoning. We first identify that this limitation arises from the attention mechanism: visual…

Cross-Modal sponsored search displays multi-modal advertisements (ads) when consumers look for desired products by natural language queries in search engines. Since multi-modal ads bring complementary details for query-ads matching, the…

Contrastive Learning (CL) performances as a rising approach to address the challenge of sparse and noisy recommendation data. Although having achieved promising results, most existing CL methods only perform either hand-crafted data or…

The surge in multimedia content has led to the development of Multi-Modal Recommender Systems (MMRecs), which use diverse modalities such as text, images, videos, and audio for more personalized recommendations. However, MMRecs struggle…

The WWW 2025 EReL@MIR Workshop Multimodal CTR Prediction Challenge focuses on effectively applying multimodal embedding features to improve click-through rate (CTR) prediction in recommender systems. This technical report presents our…

Referring Expression Comprehension (REC) is a popular multimodal task that aims to accurately detect target objects within a single image based on a given textual expression. However, due to the limitations of earlier models, traditional…

To mitigate the threat of misinformation, multimodal manipulation localization has garnered growing attention. Consider that current methods rely on costly and time-consuming fine-grained annotations, such as patch/token-level annotations.…

Multimodal models integrating natural language and visual information have substantially improved generalization of representation models. However, their effectiveness significantly declines in real-world situations where certain modalities…

Multimodal data has significantly advanced recommendation systems by integrating diverse information sources to model user preferences and item characteristics. However, these systems often struggle with redundant and irrelevant…

Deep learning recommendation systems serve personalized content under diverse tail-latency targets and input-query loads. In order to do so, state-of-the-art recommendation models rely on terabyte-scale embedding tables to learn user…

Recently, large language models (LLMs) have shown great potential in recommender systems, either improving existing recommendation models or serving as the backbone. However, there exists a large semantic gap between LLMs and recommender…

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet their positional encoding mechanisms remain suboptimal. Existing approaches uniformly assign positional indices to all tokens, overlooking…

Multimodal learning plays a critical role in e-commerce recommendation platforms today, enabling accurate recommendations and product understanding. However, existing vision-language models, such as CLIP, face key challenges in e-commerce…

Recommendation models are vital in delivering personalized user experiences by leveraging the correlation between multiple input features. However, deep learning-based recommendation models often face challenges due to evolving user…

Motion prediction is a crucial task in autonomous driving, and one of its major challenges lands in the multimodality of future behaviors. Many successful works have utilized mixture models which require identification of positive mixture…

Self-attention models have achieved state-of-the-art performance in sequential recommender systems by capturing the sequential dependencies among user-item interactions. However, they rely on positional embeddings to retain the sequential…

Nowadays, the recommendation systems are applied in the fields of e-commerce, video websites, social networking sites, etc., which bring great convenience to people's daily lives. The types of the information are diversified and abundant in…

Traditional recommender systems (RS) have been primarily optimized for accuracy and short-term engagement, often overlooking transparency and trustworthiness. Recently, platforms such as Amazon and Instagram have begun providing…

Multimodal learning robust to missing modality has attracted increasing attention due to its practicality. Existing methods tend to address it by learning a common subspace representation for different modality combinations. However, we…