Picture for Fei Yu

Fei Yu

PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods

Add code
Jul 10, 2024
Viaarxiv icon

Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation

Add code
Jul 01, 2024
Figure 1 for Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
Figure 2 for Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
Figure 3 for Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
Figure 4 for Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
Viaarxiv icon

CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding Evaluation

Add code
Jul 01, 2024
Viaarxiv icon

Towards Secure and Efficient Data Scheduling for Vehicular Social Networks

Add code
Jun 28, 2024
Viaarxiv icon

MileBench: Benchmarking MLLMs in Long Context

Add code
Apr 29, 2024
Figure 1 for MileBench: Benchmarking MLLMs in Long Context
Figure 2 for MileBench: Benchmarking MLLMs in Long Context
Figure 3 for MileBench: Benchmarking MLLMs in Long Context
Figure 4 for MileBench: Benchmarking MLLMs in Long Context
Viaarxiv icon

Outcome-supervised Verifiers for Planning in Mathematical Reasoning

Add code
Nov 16, 2023
Figure 1 for Outcome-supervised Verifiers for Planning in Mathematical Reasoning
Figure 2 for Outcome-supervised Verifiers for Planning in Mathematical Reasoning
Figure 3 for Outcome-supervised Verifiers for Planning in Mathematical Reasoning
Figure 4 for Outcome-supervised Verifiers for Planning in Mathematical Reasoning
Viaarxiv icon

A Better Match for Drivers and Riders: Reinforcement Learning at Lyft

Add code
Oct 20, 2023
Figure 1 for A Better Match for Drivers and Riders: Reinforcement Learning at Lyft
Figure 2 for A Better Match for Drivers and Riders: Reinforcement Learning at Lyft
Figure 3 for A Better Match for Drivers and Riders: Reinforcement Learning at Lyft
Figure 4 for A Better Match for Drivers and Riders: Reinforcement Learning at Lyft
Viaarxiv icon

AceGPT, Localizing Large Language Models in Arabic

Add code
Sep 22, 2023
Figure 1 for AceGPT, Localizing Large Language Models in Arabic
Figure 2 for AceGPT, Localizing Large Language Models in Arabic
Figure 3 for AceGPT, Localizing Large Language Models in Arabic
Figure 4 for AceGPT, Localizing Large Language Models in Arabic
Viaarxiv icon

AGS: An Dataset and Taxonomy for Domestic Scene Sound Event Recognition

Add code
Aug 30, 2023
Figure 1 for AGS: An Dataset and Taxonomy for Domestic Scene Sound Event Recognition
Figure 2 for AGS: An Dataset and Taxonomy for Domestic Scene Sound Event Recognition
Figure 3 for AGS: An Dataset and Taxonomy for Domestic Scene Sound Event Recognition
Figure 4 for AGS: An Dataset and Taxonomy for Domestic Scene Sound Event Recognition
Viaarxiv icon

A Huber Loss Minimization Approach to Byzantine Robust Federated Learning

Add code
Aug 24, 2023
Viaarxiv icon