Picture for Hongyu Wang

Hongyu Wang

M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal Models

May 24, 2024
Viaarxiv icon

Real-Time and Accurate: Zero-shot High-Fidelity Singing Voice Conversion with Multi-Condition Flow Synthesis

Add code
May 23, 2024
Viaarxiv icon

NGM-SLAM: Gaussian Splatting SLAM with Radiance Field Submap

May 09, 2024
Viaarxiv icon

Prompt-Guided Generation of Structured Chest X-Ray Report Using a Pre-trained LLM

Apr 17, 2024
Viaarxiv icon

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Add code
Feb 27, 2024
Viaarxiv icon

VOT: Revolutionizing Speaker Verification with Memory and Attention Mechanisms

Jan 17, 2024
Viaarxiv icon

PLE-SLAM: A Visual-Inertial SLAM Based on Point-Line Features and Efficient IMU Initialization

Add code
Jan 05, 2024
Viaarxiv icon

DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM with Joint Semantic Encoding

Jan 03, 2024
Figure 1 for DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM with Joint Semantic Encoding
Figure 2 for DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM with Joint Semantic Encoding
Figure 3 for DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM with Joint Semantic Encoding
Figure 4 for DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM with Joint Semantic Encoding
Viaarxiv icon

Temporal Adaptive RGBT Tracking with Modality Prompt

Jan 02, 2024
Viaarxiv icon

BitNet: Scaling 1-bit Transformers for Large Language Models

Oct 17, 2023
Viaarxiv icon