Related papers: MOSAIC: Multi-Domain Orthogonal Session Adaptive I…

We introduce MOSAIC (Masked Objective with Selective Adaptation for In-domain Contrastive learning), a multi-stage framework for domain adaptation of text embedding models that incorporates joint domain-specific masked supervision. Our…

Session-based recommendation focuses on predicting the next item a user will interact with based on sequences of anonymous user sessions. A significant challenge in this field is data sparsity due to the typically short-term interactions.…

Multi-behavioral sequential recommendation has recently attracted increasing attention. However, existing methods suffer from two major limitations. Firstly, user preferences and intents can be described in fine-grained detail from multiple…

A holistic understanding of object properties across diverse sensory modalities (e.g., visual, audio, and haptic) is essential for tasks ranging from object categorization to complex manipulation. Drawing inspiration from cognitive science…

Multi-subject personalized generation presents unique challenges in maintaining identity fidelity and semantic coherence when synthesizing images conditioned on multiple reference subjects. Existing methods often suffer from identity…

Cross-domain Recommendation systems leverage multi-domain user interactions to improve performance, especially in sparse data or new user scenarios. However, CDR faces challenges such as effectively capturing user preferences and avoiding…

Recommender systems have long been built upon the modeling of interactions between users and items, while recent studies have sought to broaden this paradigm by generalizing to new users and items, incorporating diverse information sources,…

In the landscape of contemporary recommender systems, user-item interactions are inherently dynamic and sequential, often characterized by various behaviors. Prior research has explored the modeling of user preferences through sequential…

Multi-domain recommender systems benefit from cross-domain representation learning and positive knowledge transfer. Both can be achieved by introducing a specific modeling of input data (i.e. disjoint history) or trying dedicated training…

We study how to allocate a fixed supervised fine-tuning budget when three objectives must be balanced at once: multi-turn safety alignment, low over-refusal on benign boundary queries, and instruction following under verifiable constraints.…

Sustaining high fidelity and high throughput of perception tasks over vision sensor streams on edge devices remains a formidable challenge, especially given the continuing increase in image sizes (e.g., generated by 4K cameras) and…

This paper proposes Medley of Sub-Attention Networks (MoSAN), a new novel neural architecture for the group recommendation task. Group-level recommendation is known to be a challenging task, in which intricate group dynamics have to be…

The problem of representative selection amounts to sampling few informative exemplars from large datasets. This paper presents MOSAIC, a novel representative selection approach from high-dimensional data that may exhibit non-linear…

Multimodal Sentiment Analysis (MSA) aims to predict sentiment from language, acoustic, and visual data in videos. However, imbalanced unimodal performance often leads to suboptimal fused representations. Existing approaches typically adopt…

Constraint inference is widely considered essential to align reinforcement learning agents with safety boundaries and operational guidelines by observing expert demonstrations. However, existing approaches typically assume homogeneous…

In the digital era, users typically interact with diverse items across multiple domains (e.g., e-commerce, streaming platforms, and social networks), generating intricate heterogeneous interaction graphs. Leveraging multi-domain data can…

User interaction data in recommender systems is a form of dyadic relation that reflects the preferences of users with items. Learning the representations of these two discrete sets of objects, users and items, is critical for…

Session-based recommendation aims to predict a user's next action based on previous actions in the current session. The major challenge is to capture authentic and complete user preferences in the entire session. Recent work utilizes graph…

We present an online multi-task learning approach for adaptive nonlinear control, which we call Online Meta-Adaptive Control (OMAC). The goal is to control a nonlinear system subject to adversarial disturbance and unknown…

The performance of multi-modal 3D occupancy prediction is limited by ineffective fusion, mainly due to geometry-semantics mismatch from fixed fusion strategies and surface detail loss caused by sparse, noisy annotations. The mismatch stems…