Related papers: Encode Me If You Can: Learning Universal User Repr…

Event log records all events that occur during the execution of business processes, so detecting and correcting anomalies in event log can provide reliable guarantee for subsequent process analysis. The previous works mainly include next…

Transformers have impressive generalization capabilities on tasks with a fixed context length. However, they fail to generalize to sequences of arbitrary length, even for seemingly simple tasks such as duplicating a string. Moreover, simply…

User representation modeling has become increasingly crucial for personalized applications, yet existing approaches struggle with generalizability across domains and sensitivity to noisy behavioral signals. We present InstructUE, an…

Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic and semantic information about the scene, much of this…

The analysis of events in dynamic environments poses a fundamental challenge in the development of intelligent agents and robots capable of interacting with humans. Current approaches predominantly utilize visual models. However, these…

An increasing number of sensors on mobile, Internet of things (IoT), and wearable devices generate time-series measurements of physical activities. Though access to the sensory data is critical to the success of many beneficial applications…

Modeling the sequential correlation of users' historical interactions is essential in sequential recommendation. However, the majority of the approaches mainly focus on modeling the \emph{intra-sequence} item correlation within each…

Getting a better understanding of user behavior is important for advancing information retrieval systems. Existing work focuses on modeling and predicting single interaction events, such as clicks. In this paper, we for the first time focus…

Modeling long histories plays a pivotal role in enhancing recommendation systems, allowing to capture user's evolving preferences, resulting in more precise and personalized recommendations. In this study we tackle the challenges of…

Recognizing human activities in videos is challenging due to the spatio-temporal complexity and context-dependence of human interactions. Prior studies often rely on single input modalities, such as RGB or skeletal data, limiting their…

Recommender systems objectives can be broadly characterized as modeling user preferences over short-or long-term time horizon. A large body of previous research studied long-term recommendation through dimensionality reduction techniques…

Sequential recommendation aims at understanding user preference by capturing successive behavior correlations, which are usually represented as the item purchasing sequences based on their past interactions. Existing efforts generally…

User response prediction, which models the user preference w.r.t. the presented items, plays a key role in online services. With two-decade rapid development, nowadays the cumulated user behavior sequences on mature Internet service…

This paper presents TCE: Temporally Coherent Embeddings for self-supervised video representation learning. The proposed method exploits inherent structure of unlabeled video data to explicitly enforce temporal coherency in the embedding…

Session-based recommendation is the task of predicting the next item a user will interact with, often without access to historical user data. In this work, we introduce Sequential Masked Modeling, a novel approach for encoder-only…

A representation is supposed universal if it encodes any element of the visual world (e.g., objects, scenes) in any configuration (e.g., scale, context). While not expecting pure universal representations, the goal in the literature is to…

Embedding models, which learn latent representations of users and items based on user-item interaction patterns, are a key component of recommendation systems. In many applications, contextual constraints need to be applied to refine…

The prevalence of wearable sensors (e.g., smart wristband) is creating unprecedented opportunities to not only inform health and wellness states of individuals, but also assess and infer personal attributes, including demographic and…

Optimizing and refining action execution through exploration and interaction is a promising way for robotic manipulation. However, practical approaches to interaction-driven robotic learning are still underexplored, particularly for…

Driving in the dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level…