HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
Paper
•
2411.02959
•
Published
•
44
papers
-
-
"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization
Paper • 2411.02355 • Published • 41 -
CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation
Paper • 2410.23090 • Published • 52 -
RARe: Retrieval Augmented Retrieval with In-Context Examples
Paper • 2410.20088 • Published • 5 -
Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss
Paper • 2410.17243 • Published • 86 -
Can Knowledge Editing Really Correct Hallucinations?
Paper • 2410.16251 • Published • 53 -
LOGO -- Long cOntext aliGnment via efficient preference Optimization
Paper • 2410.18533 • Published • 42 -
Unleashing Reasoning Capability of LLMs via Scalable Question Synthesis from Scratch
Paper • 2410.18693 • Published • 40 -
MotionCLR: Motion Generation and Training-free Editing via Understanding Attention Mechanisms
Paper • 2410.18977 • Published • 13