Accepted Papers

Similarity-based collaborative filtering (CF) models have long demonstrated strong offline performance and conceptual simplicity. However, their scalability is limited by the quadratic cost of maintaining dense item¨Citem similarity matrices. Partitioning-based paradigms have recently emerged as an...

Driven by recent breakthrough advances in neural representation learning, approximate near-neighbor (ANN) search over vector embeddings has emerged as a critical computational workload. With the introduction of the seminal Hierarchical Navigable Small World (HNSW) algorithm, graph-based indexes have...

Learned multivector representations power modern search systems with strong retrieval effectiveness, but their real-world use is limited by the high cost of exhaustive token-level retrieval. Therefore, most systems adopt a gather-and-refine strategy, where a lightweight gather phase selects candidat...

In sequential recommendation (SR), the self-attention mechanism of Transformer-based models acts as a low-pass filter, limiting their ability to capture high-frequency signals that reflect short-term user interests. To overcome this, BSARec augments the Transformer encoder with a frequency layer tha...

SEATER is a generative retrieval model that improves recommendation inference efficiency and retrieval quality by utilizing balanced tree-structured item identifiers and contrastive training objectives. We reproduce and validate SEATER¡¯s reported improvements in retrieval quality over strong base...

Large Language Models (LLMs) have been shown to have promising effectiveness in recommender systems. RecRanker, a recent LLM-based recommendation model, has demonstrated strong results on the top-$k$ recommendation task. However, the contribution of each of its core components, namely user sampling,...

ultimodal recommendation has emerged as a mainstream paradigm, typically leveraging text and visual embeddings extracted from pre-trained models such as Sentence-BERT, Vision Transformers, and ResNet. This approach is founded on the intuitive assumption that incorporating multimodal embeddings can e...

Learned sparse retrieval (LSR) is an emerging paradigm that uses pretrained language models to assign learned weights to the terms of a document, enabling practitioners to deploy next-generation rankers within their existing lexical retrieval pipelines. Although LSR systems have been found to provid...

Large Language Models (LLMs) often struggle with temporal fact conflicts due to outdated or evolving information in their training data. Two recent studies with accompanying dataset report opposite conclusions on whether external context can effectively resolve such conflicts. DYNAMICQA evaluates ho...