Related papers: Train Once, Deploy Anywhere: Matryoshka Representa…

Evaluation of multimodal reasoning models is typically reduced to a single accuracy score, implicitly treating reasoning as a unitary capability. We introduce MathLens, a benchmark of textbook-style geometry problems that exposes this…

Large Multimodal Models (LMMs) struggle to adapt varying computational budgets due to numerous visual tokens. Previous methods attempted to reduce the number of visual tokens before or within LLMs. However, these strategies inevitably…

Traditional recommender systems such as matrix factorization methods have primarily focused on learning a shared dense embedding space to represent both items and user preferences. Subsequently, sequence models such as RNN, GRUs, and,…

Text-based recommendation holds a wide range of practical applications due to its versatility, as textual descriptions can represent nearly any type of item. However, directly employing the original item descriptions may not yield optimal…

Multimodal Large Language Models (MLLMs) have shown remarkable success in comprehension tasks such as visual description and visual question answering. However, their direct application to embedding-based tasks like retrieval remains…

Any entity in the visual world can be hierarchically grouped based on shared characteristics and mapped to fine-grained sub-categories. While Multi-modal Large Language Models (MLLMs) achieve strong performance on coarse-grained visual…

This paper investigates how to better leverage large-scale pre-trained uni-modal models to further enhance discriminative multi-modal learning. Even when fine-tuned with only uni-modal data, these models can outperform previous multi-modal…

Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on…

Federated reinforcement learning (FedRL) enables multiple agents to collaboratively learn a policy without sharing their local trajectories collected during agent-environment interactions. However, in practice, the environments faced by…

Recently, relational metric learning methods have been received great attention in recommendation community, which is inspired by the translation mechanism in knowledge graph. Different from the knowledge graph where the entity-to-entity…

Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have explored using fine-tuning-based metrics, which measure the…

Recent sequential recommendation models have combined pre-trained text embeddings of items with item ID embeddings to achieve superior recommendation performance. Despite their effectiveness, the expressive power of text features in these…

MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental…

Sequential Recommender Systems (SRS), which model a user's interaction history to predict the next item of interest, are widely used in various applications. However, existing SRS often struggle with low-popularity items, a challenge known…

Compositional generalization in sequential decision-making requires identifying which parts of prior rollouts remain useful for new tasks. Existing methods reuse skills or predictive models, but often overlook rich local transition geometry…

Sequential recommendation plays a critical role in modern online platforms such as e-commerce, advertising, and content streaming, where accurately predicting users' next interactions is essential for personalization. Recent…

Recent advances in Large Language Models (LLMs) have demonstrated significant potential in the field of Recommendation Systems (RSs). Most existing studies have focused on converting user behavior logs into textual prompts and leveraging…

Modern DNN-based recommendation systems rely on training-derived embeddings of sparse features. Input sparsity makes obtaining high-quality embeddings for rarely-occurring categories harder as their representations are updated infrequently.…

General recommender systems deliver personalized services by learning user and item representations, with the central challenge being how to capture latent user preferences. However, representations derived from sparse interactions often…

While session-based recommender systems (SBRSs) have shown superior recommendation performance, multi-task learning (MTL) has been adopted by SBRSs to enhance their prediction accuracy and generalizability further. Hierarchical MTL (H-MTL)…