Xiaodong Han
6 papers · 2022–2024 · 6 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 · Silver
🗺️
Taxonomy Completionist
(26)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Deep Learning
(6)
Artificial Intelligence
(5)
Core AI
(5)
Machine Learning
(4)
Learning Types
(4)
Computer Vision
(3)
Natural Language Processing
(3)
Application Areas
(2)
Architectures
(2)
Generation · Computer Vision
(2)
Generation · Natural Language Processing
(2)
Optimization & Theory · Machine Learning
(2)
Optimization & Theory · Deep Learning
(2)
Processing
(2)
Analysis
(1)
Keywords
multimodal learning
(3)
video understanding
(3)
video captioning
(2)
language modeling
(2)
text classification
(1)
video generation
(1)
motion estimation
(1)
attention mechanism
(1)
temporal reasoning
(1)
audio-visual learning
(1)
video-text alignment
(1)
memory optimization
(1)
inference optimization
(1)
kv cache compression
(1)
inference acceleration
(1)
kv cache
(1)
linear transformer
(1)
dense caption
(1)
position embedding
(1)
bidirectional generation
(1)
Papers
Improving Audio-Visual Segmentation with Bidirectional Generation
AAAI 2024
PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference
ACL 2024
Vript: A Video Is Worth Thousands of Words
NeurIPS 2024
Fine-Grained Audible Video Description
CVPR 2023
Toeplitz Neural Network for Sequence Modeling
ICLR 2023
The Devil in Linear Transformer
EMNLP 2022