Leqi Shen
6 papers · 2022–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(23)
⚡
Prolific Year · Productive
Top co-authors
Research topics
Machine Learning
(5)
Application Areas
(5)
Deep Learning
(4)
Artificial Intelligence
(3)
Computer Vision
(3)
Core AI · Artificial Intelligence
(3)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Models
(2)
Techniques
(2)
Analysis
(1)
Core AI · Computer Vision
(1)
Core Methods
(1)
Generation
(1)
Learning Paradigms
(1)
Keywords
knowledge distillation
(2)
feature alignment
(1)
representation learning
(1)
feature learning
(1)
video understanding
(1)
person re-identification
(1)
unsupervised domain adaptation
(1)
feature space
(1)
cross-modal alignment
(1)
parameter-efficient fine-tuning
(1)
vision-language model
(1)
token pruning
(1)
pseudo label
(1)
video-text retrieval
(1)
visual token compression
(1)
parameter-efficient adaptation
(1)
student model
(1)
text-video retrieval
(1)
token merging
(1)
teacher model
(1)
Papers
AdaTP: Attention-Debiased Token Pruning for Video Large Language Models
EMNLP 2025
Beyond Logits: Aligning Feature Dynamics for Effective Knowledge Distillation
ACL 2025
DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
CVPR 2025
Follow-Your-Click: Open-domain Regional Image Animation via Motion Prompts
AAAI 2025
TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
ICLR 2025
SECRET: Self-Consistent Pseudo Label Refinement for Unsupervised Domain Adaptive Person Re-identification
AAAI 2022