HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
Paper
•
2411.02959
•
Published
•
64
papers
-
-
"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization
Paper • 2411.02355 • Published • 46 -
CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation
Paper • 2410.23090 • Published • 53 -
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 • 88 -
Can Knowledge Editing Really Correct Hallucinations?
Paper • 2410.16251 • Published • 54 -
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 • 14 -
Balancing Pipeline Parallelism with Vocabulary Parallelism
Paper • 2411.05288 • Published • 19 -
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding
Paper • 2411.04952 • Published • 27 -
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
Paper • 2411.04905 • Published • 110 -
Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion
Paper • 2412.04424 • Published • 50 -
VisionZip: Longer is Better but Not Necessary in Vision Language Models
Paper • 2412.04467 • Published • 96 -
PaliGemma 2: A Family of Versatile VLMs for Transfer
Paper • 2412.03555 • Published • 110 -
Imagine360: Immersive 360 Video Generation from Perspective Anchor
Paper • 2412.03552 • Published • 26