Abstract page for arXiv paper 2412.04604: ARC Prize 2024: Technical Report
Abstract page for arXiv paper 2412.13663: Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Abstract page for arXiv paper 2502.03979: Towards Unified Music Emotion Recognition across Dimensional and Categorical Models
Abstract page for arXiv paper 2505.24226: E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness
arXiv is a forum for professional members of the scientific community, providing rapid distribution of new research. As part of the service all submissions are subject to moderation. Material submitted to arXiv is expected to be self-contained and of interest, relevance, and value to the...
Abstract page for arXiv paper 2402.17645v1: SongComposer: A Large Language Model for Lyric and Melody Composition in Song Generation
Abstract page for arXiv paper 2404.04044v2: A Comparison of Methods for Evaluating Generative IR
Abstract page for arXiv paper 2409.07500v1: DV-FSR: A Dual-View Target Attack Framework for Federated Sequential Recommendation
Much of the evaluation and tuning of a search system relies on relevance labels—annotations that say whether a document is useful for a given search and searcher. Ideally these come from real searchers, but it is hard to collect this data at scale, so typical experiments rely on third-party...
Creating lyrics and melodies for the vocal track in a symbolic format, known as song composition, demands expert musical knowledge of melody, an advanced understanding of lyrics, and precise alignment between them. Despite achievements in sub-tasks such as lyric generation, lyric-to-melody, and...