HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
Paper
• 2411.02959 • Published
• 71
papers
-
-
"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization
Paper • 2411.02355 • Published • 51 -
CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation
Paper • 2410.23090 • Published • 55 -
RARe: Retrieval Augmented Retrieval with In-Context Examples
Paper • 2410.20088 • Published • 4 -
Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss
Paper • 2410.17243 • Published • 92 -
Can Knowledge Editing Really Correct Hallucinations?
Paper • 2410.16251 • Published • 55 -
LOGO -- Long cOntext aliGnment via efficient preference Optimization
Paper • 2410.18533 • Published • 43 -
Unleashing Reasoning Capability of LLMs via Scalable Question Synthesis from Scratch
Paper • 2410.18693 • Published • 42 -
MotionCLR: Motion Generation and Training-free Editing via Understanding Attention Mechanisms
Paper • 2410.18977 • Published • 15 -
Balancing Pipeline Parallelism with Vocabulary Parallelism
Paper • 2411.05288 • Published • 20 -
M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding
Paper • 2411.04952 • Published • 29 -
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
Paper • 2411.04905 • Published • 127 -
Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion
Paper • 2412.04424 • Published • 62 -
VisionZip: Longer is Better but Not Necessary in Vision Language Models
Paper • 2412.04467 • Published • 117 -
PaliGemma 2: A Family of Versatile VLMs for Transfer
Paper • 2412.03555 • Published • 133 -
Imagine360: Immersive 360 Video Generation from Perspective Anchor
Paper • 2412.03552 • Published • 29 -
RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
Paper • 2412.13746 • Published • 9 -
Are Your LLMs Capable of Stable Reasoning?
Paper • 2412.13147 • Published • 93 -
OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain
Paper • 2412.13018 • Published • 41 -
VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation
Paper • 2412.10704 • Published • 16 -
SUGAR: Subject-Driven Video Customization in a Zero-Shot Manner
Paper • 2412.10533 • Published • 5 -
When to Speak, When to Abstain: Contrastive Decoding with Abstention
Paper • 2412.12527 • Published • 4 -
RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation
Paper • 2412.11919 • Published • 36 -
Smaller Language Models Are Better Instruction Evolvers
Paper • 2412.11231 • Published • 28 -
VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping
Paper • 2412.11279 • Published • 13 -
SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video
Paper • 2412.09982 • Published • 7 -
TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning
Paper • 2412.10447 • Published • 5 -
Whisper-GPT: A Hybrid Representation Audio Large Language Model
Paper • 2412.11449 • Published • 4 -
GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training
Paper • 2412.11863 • Published • 4 -
Reliable, Reproducible, and Really Fast Leaderboards with Evalica
Paper • 2412.11314 • Published • 2 -
GenEx: Generating an Explorable World
Paper • 2412.09624 • Published • 98 -
1.58-bit FLUX
Paper • 2412.18653 • Published • 86 -
Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
Paper • 2412.18319 • Published • 39 -
BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning
Paper • 2501.03226 • Published • 43 -
SearchRAG: Can Search Engines Be Helpful for LLM-based Medical Question Answering?
Paper • 2502.13233 • Published • 15 -
SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference
Paper • 2502.18137 • Published • 60 -
GCC: Generative Color Constancy via Diffusing a Color Checker
Paper • 2502.17435 • Published • 29 -
Self-rewarding correction for mathematical reasoning
Paper • 2502.19613 • Published • 82 -
Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows
Paper • 2512.13168 • Published • 52