Pengzhang Liu
7 papers · 2022–2026 · 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
(21)
Venues
Top co-authors
Research topics
Machine Learning
(7)
Application Areas
(5)
Core Methods
(5)
Artificial Intelligence
(4)
Learning Types · Machine Learning
(4)
Deep Learning
(3)
Core AI
(3)
Learning Paradigms
(2)
Learning Types · Deep Learning
(2)
Computer Vision
(1)
Natural Language Processing
(1)
Applications
(1)
Models
(1)
Optimization & Theory
(1)
Processing
(1)
Keywords
representation learning
(2)
knowledge distillation
(2)
vision-language model
(2)
multi-task learning
(1)
feature learning
(1)
feature distribution
(1)
self-supervised learning
(1)
text generation
(1)
language modeling
(1)
multimodal learning
(1)
prompt learning
(1)
deep learning
(1)
subset selection
(1)
cross-modal alignment
(1)
parameter-efficient fine-tuning
(1)
noise injection
(1)
data efficiency
(1)
video-text retrieval
(1)
multi-label recognition
(1)
parameter-efficient adaptation
(1)
Papers
FANoise: Singular Value-Adaptive Noise Modulation for Robust Multimodal Representation Learning
AAAI 2026
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
TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
ICLR 2025
DynaMS: Dyanmic Margin Selection for Efficient Deep Learning
ICLR 2023
Exploring Structured Semantic Prior for Multi Label Recognition With Incomplete Labels
CVPR 2023
LEGO-ABSA: A Prompt-based Task Assemblable Unified Generative Framework for Multi-task Aspect-based Sentiment Analysis
COLING 2022