Related papers: Universal Retrieval for Multimodal Trajectory Mode…

Accurate travel time estimation (TTE) plays a crucial role in intelligent transportation systems. However, it remains challenging due to heterogeneous data sources and complex traffic dynamics. Moreover, traditional approaches typically…

Agentic search has recently emerged as a powerful paradigm, where an agent interleaves multi-step reasoning with on-demand retrieval to solve complex questions. Despite its success, how to design a retriever for agentic search remains…

Information retrieval (IR) systems have traditionally been designed and trained for human users, with learning-to-rank methods relying heavily on large-scale human interaction logs such as clicks and dwell time. With the rapid emergence of…

Generalizing deep reinforcement learning agents to unseen environments remains a significant challenge. One promising solution is Unsupervised Environment Design (UED), a co-evolutionary framework in which a teacher adaptively generates…

Existing information retrieval (IR) models often assume a homogeneous format, limiting their applicability to diverse user needs, such as searching for images with text descriptions, searching for a news article with a headline image, or…

Multi-agent trajectory data collected from domains such as team sports often suffer from missing values due to various factors. While many imputation methods have been proposed for spatiotemporal data, they are not well-suited for…

Generative retrieval is an emerging approach in information retrieval that generates identifiers (IDs) of target data based on a query, providing an efficient alternative to traditional embedding-based retrieval methods. However, existing…

Universal multimodal retrieval (UMR), which aims to address complex retrieval tasks where both queries and candidates span diverse modalities, has been significantly advanced by the emergence of MLLMs. While state-of-the-art MLLM-based…

The widespread adoption of mobile devices and data collection technologies has led to an exponential increase in trajectory data, presenting significant challenges in spatio-temporal data mining, particularly for efficient and accurate…

Trajectory modeling, which includes research on trajectory data pattern mining and future prediction, has widespread applications in areas such as life services, urban transportation, and public administration. Numerous methods have been…

Understanding natural-language references to objects in dynamic 3D driving scenes is essential for interactive autonomous systems. In practice, many referring expressions describe targets through recent motion or short-term interactions,…

In-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction. It has been shown highly dependent on the provided…

Multi-agent trajectory prediction is crucial for various practical applications, spurring the construction of many large-scale trajectory datasets, including vehicles and pedestrians. However, discrepancies exist among datasets due to…

Unsupervised Environment Design (UED) is a paradigm for automatically generating a curriculum of training environments, enabling agents trained in these environments to develop general capabilities, i.e., achieving good zero-shot transfer…

We present Omni-Embed-Nemotron, a unified multimodal retrieval embedding model developed to handle the increasing complexity of real-world information needs. While Retrieval-Augmented Generation (RAG) has significantly advanced language…

An open problem in Machine Learning is how to avoid models to exploit spurious correlations in the data; a famous example is the background-label shortcut in the Waterbirds dataset. A common remedy is to train a model across multiple…

We introduce UGen, a unified autoregressive multimodal model that demonstrates strong performance across text processing, image understanding, and image generation tasks simultaneously. UGen converts both texts and images into discrete…

With the rapid advancement of multimodal retrieval and its application in LLMs and multimodal LLMs, increasingly complex retrieval tasks have emerged. Existing methods predominantly rely on task-specific fine-tuning of vision-language…

Most text retrievers generate \emph{one} query vector to retrieve relevant documents. Yet, the conditional distribution of relevant documents for the query may be multimodal, e.g., representing different interpretations of the query. We…

Embodied AI (EAI) agents continuously interact with the physical world, generating vast, heterogeneous multimodal data streams that traditional management systems are ill-equipped to handle. In this survey, we first systematically evaluate…