HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems Paper • 2411.02959 • Published 5 days ago • 52
Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks Paper • 2411.01192 • Published 8 days ago • 3
FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models Paper • 2402.10986 • Published Feb 16 • 76
SPAR: Personalized Content-Based Recommendation via Long Engagement Attention Paper • 2402.10555 • Published Feb 16 • 32