Related papers: Multimodal Query Suggestion with Multi-Agent Reinf…

Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks…

Conversational recommender systems (CRSs) aim to recommend high-quality items to users through a dialogue interface. It usually contains multiple sub-tasks, such as user preference elicitation, recommendation, explanation, and item…

Sequential recommendation aims to predict a user's next action in large-scale recommender systems. While traditional methods often suffer from insufficient information interaction, recent generative recommendation models partially address…

Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often generate a single query for retrieval at each reasoning step, limiting information…

We aim to develop a multimodal research agent capable of explicit reasoning and planning, multi-tool invocation, and cross-modal information synthesis, enabling it to conduct deep research tasks. However, we observe three main challenges in…

Document Visual Question Answering (DocVQA) faces dual challenges in processing lengthy multimodal documents (text, images, tables) and performing cross-modal reasoning. Current document retrieval-augmented generation (DocRAG) methods…

Multiple choice questions (MCQs) are a popular method for evaluating students' knowledge due to their efficiency in administration and grading. Crafting high-quality math MCQs is a labor-intensive process that requires educators to…

Multimodal Retrieval Augmented Generation (MRAG) systems have shown promise in enhancing the generation capabilities of multimodal large language models (MLLMs). However, existing MRAG frameworks primarily adhere to rigid, single-step…

Retrieval augmented generation (RAG) has shown great power in improving Large Language Models (LLMs). However, most existing RAG-based LLMs are dedicated to retrieving single modality information, mainly text; while for many real-world…

Sequential Recommendation (SR) aims to predict future user-item interactions based on historical interactions. While many SR approaches concentrate on user IDs and item IDs, the human perception of the world through multi-modal signals,…

Visual Question-Answering (VQA) is a challenging multimodal task that requires integrating visual and textual information to generate accurate responses. While multimodal Retrieval-Augmented Generation (mRAG) has shown promise in enhancing…

Retrieval-based multi-image question answering (QA) task involves retrieving multiple question-related images and synthesizing these images to generate an answer. Conventional "retrieve-then-answer" pipelines often suffer from cascading…

Inspirational search, the process of exploring designs to inform and inspire new creative work, is pivotal in mobile user interface (UI) design. However, exploring the vast space of UI references remains a challenge. Existing AI-based UI…

Large language models often encounter challenges with static knowledge and hallucinations, which undermine their reliability. Retrieval-augmented generation (RAG) mitigates these issues by incorporating external information. However, user…

Understanding multimodal long-context documents that comprise multimodal chunks such as paragraphs, figures, and tables is challenging due to (1) cross-modal heterogeneity to localize relevant information across modalities, (2) cross-page…

Retrieval-augmented generation with tool-calling agents (agentic RAG) has become increasingly powerful in understanding, processing, and responding to user queries. However, the scope of the grounding knowledge is limited and asking…

Visual Question Answering (VQA) often requires coupling fine-grained perception with factual knowledge beyond the input image. Prior multimodal Retrieval-Augmented Generation (MM-RAG) systems improve factual grounding but lack an internal…

Recently, there has been growing interest in developing the next-generation recommender systems (RSs) based on pretrained large language models (LLMs). However, the semantic gap between natural language and recommendation tasks is still not…

Large language models (LLMs) have recently been adopted for recommendations due to their ability to understand user intent and item semantics. However, LLM-based recommender systems often rely on parametric knowledge and suffer from…

In modern search systems, search engines often suggest relevant queries to users through various panels or components, helping refine their information needs. Traditionally, these recommendations heavily rely on historical search logs to…