Picture for Fan Mo

Fan Mo

Round Attention: A Novel Round-Level Attention Mechanism to Accelerate LLM Inference

Add code
Feb 21, 2025
Viaarxiv icon

Personalized Fashion Recommendation with Image Attributes and Aesthetics Assessment

Add code
Jan 06, 2025
Viaarxiv icon

KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosis

Add code
Dec 22, 2024
Viaarxiv icon

Data-Efficient Massive Tool Retrieval: A Reinforcement Learning Approach for Query-Tool Alignment with Language Models

Add code
Oct 04, 2024
Figure 1 for Data-Efficient Massive Tool Retrieval: A Reinforcement Learning Approach for Query-Tool Alignment with Language Models
Figure 2 for Data-Efficient Massive Tool Retrieval: A Reinforcement Learning Approach for Query-Tool Alignment with Language Models
Figure 3 for Data-Efficient Massive Tool Retrieval: A Reinforcement Learning Approach for Query-Tool Alignment with Language Models
Figure 4 for Data-Efficient Massive Tool Retrieval: A Reinforcement Learning Approach for Query-Tool Alignment with Language Models
Viaarxiv icon

Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrieval

Add code
May 10, 2024
Viaarxiv icon

Centaur: Federated Learning for Constrained Edge Devices

Add code
Nov 12, 2022
Viaarxiv icon

SoK: Machine Learning with Confidential Computing

Add code
Aug 22, 2022
Figure 1 for SoK: Machine Learning with Confidential Computing
Figure 2 for SoK: Machine Learning with Confidential Computing
Figure 3 for SoK: Machine Learning with Confidential Computing
Figure 4 for SoK: Machine Learning with Confidential Computing
Viaarxiv icon

Towards Battery-Free Machine Learning and Inference in Underwater Environments

Add code
Feb 16, 2022
Figure 1 for Towards Battery-Free Machine Learning and Inference in Underwater Environments
Figure 2 for Towards Battery-Free Machine Learning and Inference in Underwater Environments
Figure 3 for Towards Battery-Free Machine Learning and Inference in Underwater Environments
Figure 4 for Towards Battery-Free Machine Learning and Inference in Underwater Environments
Viaarxiv icon

Quantifying Information Leakage from Gradients

Add code
May 28, 2021
Figure 1 for Quantifying Information Leakage from Gradients
Figure 2 for Quantifying Information Leakage from Gradients
Figure 3 for Quantifying Information Leakage from Gradients
Figure 4 for Quantifying Information Leakage from Gradients
Viaarxiv icon

PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments

Add code
Apr 29, 2021
Figure 1 for PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments
Figure 2 for PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments
Figure 3 for PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments
Figure 4 for PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments
Viaarxiv icon