StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization Paper • 2410.08815 • Published 21 days ago • 39
Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens Paper • 2410.13863 • Published 15 days ago • 35
PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment Paper • 2410.13785 • Published 15 days ago • 18
BenTo: Benchmark Task Reduction with In-Context Transferability Paper • 2410.13804 • Published 15 days ago • 20
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines Paper • 2410.12705 • Published 16 days ago • 29
MoH: Multi-Head Attention as Mixture-of-Head Attention Paper • 2410.11842 • Published 17 days ago • 20
DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control Paper • 2410.13830 • Published 15 days ago • 23
JudgeBench: A Benchmark for Evaluating LLM-based Judges Paper • 2410.12784 • Published 16 days ago • 33
RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation Paper • 2408.02545 • Published Aug 5 • 33
MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery Paper • 2409.05591 • Published Sep 9 • 28
MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models Paper • 2410.13085 • Published 16 days ago • 20