Picture for Hui Xiong

Hui Xiong

Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding

Add code
Mar 17, 2025
Viaarxiv icon

Cognitive Disentanglement for Referring Multi-Object Tracking

Add code
Mar 14, 2025
Viaarxiv icon

From Understanding to Excelling: Template-Free Algorithm Design through Structural-Functional Co-Evolution

Add code
Mar 13, 2025
Viaarxiv icon

Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attacks

Add code
Mar 13, 2025
Viaarxiv icon

Talk2PC: Enhancing 3D Visual Grounding through LiDAR and Radar Point Clouds Fusion for Autonomous Driving

Add code
Mar 11, 2025
Viaarxiv icon

Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking

Add code
Mar 06, 2025
Viaarxiv icon

Simulating the Real World: A Unified Survey of Multimodal Generative Models

Add code
Mar 06, 2025
Figure 1 for Simulating the Real World: A Unified Survey of Multimodal Generative Models
Figure 2 for Simulating the Real World: A Unified Survey of Multimodal Generative Models
Figure 3 for Simulating the Real World: A Unified Survey of Multimodal Generative Models
Figure 4 for Simulating the Real World: A Unified Survey of Multimodal Generative Models
Viaarxiv icon

TimeFound: A Foundation Model for Time Series Forecasting

Add code
Mar 06, 2025
Viaarxiv icon

SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction

Add code
Mar 05, 2025
Viaarxiv icon

Can Large Language Models Help Experimental Design for Causal Discovery?

Add code
Mar 04, 2025
Viaarxiv icon