DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation
Paper
• 2410.00201 • Published
AI Papers
-
-
Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems
Paper • 2409.19804 • Published -
Rethinking Conventional Wisdom in Machine Learning: From Generalization to Scaling
Paper • 2409.15156 • Published -
Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue
Paper • 2409.04927 • Published -
Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers
Paper • 2410.02642 • Published -
L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?
Paper • 2410.02115 • Published • 10 -
Distilling an End-to-End Voice Assistant Without Instruction Training Data
Paper • 2410.02678 • Published • 23 -
Contrastive Localized Language-Image Pre-Training
Paper • 2410.02746 • Published • 37 -
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
Paper • 2410.02073 • Published • 42 -
SpreadsheetLLM: Encoding Spreadsheets for Large Language Models
Paper • 2407.09025 • Published • 139 -
EmbedLLM: Learning Compact Representations of Large Language Models
Paper • 2410.02223 • Published • 3 -
ToolGen: Unified Tool Retrieval and Calling via Generation
Paper • 2410.03439 • Published • 1 -
TableRAG: Million-Token Table Understanding with Language Models
Paper • 2410.04739 • Published • 1 -
Differential Transformer
Paper • 2410.05258 • Published • 180 -
Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
Paper • 2410.05983 • Published • 2 -
SEGMENT+: Long Text Processing with Short-Context Language Models
Paper • 2410.06519 • Published -
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
Paper • 2410.08815 • Published • 47 -
VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
Paper • 2410.10594 • Published • 29 -
Harnessing Webpage UIs for Text-Rich Visual Understanding
Paper • 2410.13824 • Published • 30 -
Optimizing Retrieval-Augmented Generation with Elasticsearch for Enhanced Question-Answering Systems
Paper • 2410.14167 • Published -
Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping
Paper • 2410.16232 • Published -
LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering
Paper • 2410.18050 • Published -
ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems
Paper • 2410.19572 • Published • 1 -
Large Language Models Reflect the Ideology of their Creators
Paper • 2410.18417 • Published -
Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval
Paper • 2410.23214 • Published -
Search Engines in an AI Era: The False Promise of Factual and Verifiable Source-Cited Responses
Paper • 2410.22349 • Published -
Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models
Paper • 2411.00492 • Published • 6 -
CORAG: A Cost-Constrained Retrieval Optimization System for Retrieval-Augmented Generation
Paper • 2411.00744 • Published -
Long Context RAG Performance of Large Language Models
Paper • 2411.03538 • Published • 1 -
From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models
Paper • 2411.05036 • Published • 1 -
Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
Paper • 2411.06037 • Published • 1 -
DataLab: A Unifed Platform for LLM-Powered Business Intelligence
Paper • 2412.02205 • Published