Picture for Yi Luan

Yi Luan

Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?

Add code
Jun 19, 2024
Figure 1 for Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?
Figure 2 for Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?
Figure 3 for Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?
Figure 4 for Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?
Viaarxiv icon

Gecko: Versatile Text Embeddings Distilled from Large Language Models

Add code
Mar 29, 2024
Figure 1 for Gecko: Versatile Text Embeddings Distilled from Large Language Models
Figure 2 for Gecko: Versatile Text Embeddings Distilled from Large Language Models
Figure 3 for Gecko: Versatile Text Embeddings Distilled from Large Language Models
Figure 4 for Gecko: Versatile Text Embeddings Distilled from Large Language Models
Viaarxiv icon

MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions

Add code
Mar 28, 2024
Figure 1 for MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
Figure 2 for MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
Figure 3 for MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
Figure 4 for MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
Viaarxiv icon

Gemini: A Family of Highly Capable Multimodal Models

Add code
Dec 19, 2023
Viaarxiv icon

Instruction-Following Evaluation for Large Language Models

Add code
Nov 14, 2023
Figure 1 for Instruction-Following Evaluation for Large Language Models
Figure 2 for Instruction-Following Evaluation for Large Language Models
Figure 3 for Instruction-Following Evaluation for Large Language Models
Figure 4 for Instruction-Following Evaluation for Large Language Models
Viaarxiv icon

Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities

Add code
Feb 24, 2023
Figure 1 for Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities
Figure 2 for Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities
Figure 3 for Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities
Figure 4 for Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities
Viaarxiv icon

Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?

Add code
Feb 24, 2023
Figure 1 for Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?
Figure 2 for Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?
Figure 3 for Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?
Figure 4 for Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?
Viaarxiv icon

Promptagator: Few-shot Dense Retrieval From 8 Examples

Add code
Sep 23, 2022
Figure 1 for Promptagator: Few-shot Dense Retrieval From 8 Examples
Figure 2 for Promptagator: Few-shot Dense Retrieval From 8 Examples
Figure 3 for Promptagator: Few-shot Dense Retrieval From 8 Examples
Figure 4 for Promptagator: Few-shot Dense Retrieval From 8 Examples
Viaarxiv icon

ASQA: Factoid Questions Meet Long-Form Answers

Add code
Apr 12, 2022
Figure 1 for ASQA: Factoid Questions Meet Long-Form Answers
Figure 2 for ASQA: Factoid Questions Meet Long-Form Answers
Figure 3 for ASQA: Factoid Questions Meet Long-Form Answers
Figure 4 for ASQA: Factoid Questions Meet Long-Form Answers
Viaarxiv icon

CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning

Add code
Dec 16, 2021
Figure 1 for CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning
Figure 2 for CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning
Figure 3 for CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning
Figure 4 for CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning
Viaarxiv icon