Related papers: TriAlignGR: Triangular Multitask Alignment with Mu…

Multimodal recommendation combines the user historical behaviors with the modal features of items to capture the tangible user preferences, presenting superior performance compared to the conventional ID-based recommender systems. However,…

Large Language Models (LLMs) demonstrate significant advantages in leveraging structured world knowledge and multi-step reasoning capabilities. However, fundamental challenges arise when transforming LLMs into real-world recommender systems…

Scene Graph Generation (SGG) aims to structurally and comprehensively represent objects and their connections in images, it can significantly benefit scene understanding and other related downstream tasks. Existing SGG models often struggle…

Large-scale short-video search ranking models are typically trained on sparse co-occurrence signals over hashed item identifiers (HIDs). While effective at memorizing frequent interactions, such ID-based models struggle to generalize to…

Multi-modal recommendation greatly enhances the performance of recommender systems by modeling the auxiliary information from multi-modality contents. Most existing multi-modal recommendation models primarily exploit multimedia information…

The exponential growth of online content has posed significant challenges to ID-based models in industrial recommendation systems, ranging from extremely high cardinality and dynamically growing ID space, to highly skewed engagement…

The primary focus of most recent works on open-vocabulary neural fields is extracting precise semantic features from the VLMs and then consolidating them efficiently into a multi-view consistent 3D neural fields representation. However,…

Multilingual Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to perform knowledge-intensive tasks in multilingual settings by leveraging retrieved documents as external evidence. However, when the retrieved…

Enabling natural communication through brain-computer interfaces (BCIs) remains one of the most profound challenges in neuroscience and neurotechnology. While existing frameworks offer partial solutions, they are constrained by…

3D Visual Grounding (3DVG) focuses on locating objects in 3D scenes based on natural language descriptions, serving as a fundamental task for embodied AI and robotics. Recent advances in Multi-modal Large Language Models (MLLMs) have…

The goal of sequential recommendation (SR) is to predict a user's potential interested items based on her/his historical interaction sequences. Most existing sequential recommenders are developed based on ID features, which, despite their…

The goal of Text-to-Image Person Retrieval (TIPR) is to retrieve specific person images according to the given textual descriptions. A primary challenge in this task is bridging the substantial representational gap between visual and…

Multimodal large language models (MLLMs) have achieved significant progress in image and language tasks due to the strong reasoning capability of large language models (LLMs). Nevertheless, most MLLMs suffer from limited spatial reasoning…

Semantic IDs are discrete identifiers generated by quantizing the Multi-modal Large Language Models (MLLMs) embeddings, enabling efficient multi-modal content integration in recommendation systems. However, their lack of collaborative…

High-quality 3D assets are essential for VR/AR, industrial design, and entertainment, motivating growing interest in generative models that create 3D content from user prompts. Most existing 3D generators, however, rely on a single…

Generative recommendation frameworks typically represent items as discrete Semantic IDs (SIDs). While existing studies have sought to enhance SID construction by incorporating multimodal content, collaborative signals, or more advanced…

Scene Graph Generation (SGG) suffers from a long-tailed distribution, where a few predicate classes dominate while many others are underrepresented, leading to biased models that underperform on rare relations. Unbiased-SGG methods address…

Generative recommendation provides a novel paradigm in which each item is represented by a discrete semantic ID (SID) learned from rich content. Most existing methods treat SIDs as predefined and train recommenders under static indexing. In…

Generative recommendation (GR) has become a powerful paradigm in recommendation systems that implicitly links modality and semantics to item representation, in contrast to previous methods that relied on non-semantic item identifiers in…

This paper addresses the challenge of building multimodal recommender systems for the movie domain, where sparse item metadata (e.g., title and genres) can limit retrieval quality and downstream recommendations. We introduce RAG-VisualRec,…