Picture for Hongyang Zhang

Hongyang Zhang

Prediction of Halo Coronal Mass Ejections Using SDO/HMI Vector Magnetic Data Products and a Transformer Model

Add code
Mar 05, 2025
Viaarxiv icon

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Add code
Mar 03, 2025
Viaarxiv icon

An Interpretable Machine Learning Approach to Understanding the Relationships between Solar Flares and Source Active Regions

Add code
Feb 20, 2025
Viaarxiv icon

Encrypted Large Model Inference: The Equivariant Encryption Paradigm

Add code
Feb 03, 2025
Viaarxiv icon

The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control

Add code
Dec 04, 2024
Figure 1 for The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control
Figure 2 for The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control
Figure 3 for The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control
Figure 4 for The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control
Viaarxiv icon

Wireless Communications in Doubly Selective Channels with Domain Adaptivity

Add code
Aug 01, 2024
Figure 1 for Wireless Communications in Doubly Selective Channels with Domain Adaptivity
Figure 2 for Wireless Communications in Doubly Selective Channels with Domain Adaptivity
Figure 3 for Wireless Communications in Doubly Selective Channels with Domain Adaptivity
Figure 4 for Wireless Communications in Doubly Selective Channels with Domain Adaptivity
Viaarxiv icon

Complete Security and Privacy for AI Inference in Decentralized Systems

Add code
Jul 28, 2024
Figure 1 for Complete Security and Privacy for AI Inference in Decentralized Systems
Figure 2 for Complete Security and Privacy for AI Inference in Decentralized Systems
Figure 3 for Complete Security and Privacy for AI Inference in Decentralized Systems
Figure 4 for Complete Security and Privacy for AI Inference in Decentralized Systems
Viaarxiv icon

Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification

Add code
Jul 10, 2024
Figure 1 for Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification
Figure 2 for Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification
Figure 3 for Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification
Figure 4 for Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification
Viaarxiv icon

BACON: Supercharge Your VLM with Bag-of-Concept Graph to Mitigate Hallucinations

Add code
Jul 03, 2024
Figure 1 for BACON: Supercharge Your VLM with Bag-of-Concept Graph to Mitigate Hallucinations
Figure 2 for BACON: Supercharge Your VLM with Bag-of-Concept Graph to Mitigate Hallucinations
Figure 3 for BACON: Supercharge Your VLM with Bag-of-Concept Graph to Mitigate Hallucinations
Figure 4 for BACON: Supercharge Your VLM with Bag-of-Concept Graph to Mitigate Hallucinations
Viaarxiv icon

EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees

Add code
Jun 24, 2024
Viaarxiv icon