Lv Tang
Scholar

Lv Tang

Google Scholar ID: BSTLuZcAAAAJ
University of Alberta. Former researcher @ UCAS/Nanjing University
Computer VisionMLLMVideo CompressionImage Segmentation
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,004
 
H-index
15
 
i10-index
19
 
Publications
20
 
Co-authors
1
list available
Contact
Emailluckybird1994@gmail.comCVOpen ↗TwitterOpen ↗GitHubOpen ↗
Publications
9 items
InfoTok: Regulating Information Flow for Capacity-Constrained Shared Visual Tokenization in Unified MLLMs
2026
Cited
0
Video Compression with Hierarchical Temporal Neural Representation
2026
Cited
0
Frequency-aware Neural Representation for Videos
2026
Cited
0
UNeMo: Collaborative Visual-Language Reasoning and Navigation via a Multimodal World Model
2025
Cited
0
SANR: Scene-Aware Neural Representation for Light Field Image Compression with Rate-Distortion Optimization
2025
Cited
0
MSNeRV: Neural Video Representation with Multi-Scale Feature Fusion
2025
Cited
0
Scaling Vision Mamba Across Resolutions via Fractal Traversal
2025
Cited
0
UAR-NVC: A Unified AutoRegressive Framework for Memory-Efficient Neural Video Compression
2025
Cited
0
Resume (English only)
Academic Achievements
  • Published 10 papers in top-tier conferences and journals, with a total of 29 publications and over 890 citations
  • 2025: One paper accepted by Neural Networks
  • 2024: Papers accepted by TOMM (2), AAAI 2025, ACMMM 2024, IJCV 2024, CVPR 2024
  • Selected publications include AAAI 2025 (Oral), ACMMM 2024, IJCV 2024, CVPR 2024, TCSVT 2024, ICCV 2023, TIP 2022, CVPR 2022, ICCV 2021
  • Served as corresponding author or co-first author on multiple papers
Co-authors
1 total
Bo Li
Bo Li
vivo Mobile Communication. Former researcher @ Tencent Youtu Lab/ Nanjing University