Zihan Song
4 papers · 2021–2026 · 4 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 · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(14)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Artificial Intelligence
(3)
Deep Learning
(3)
Core AI
(3)
Computer Vision
(1)
Data Science & Analytics
(1)
Machine Learning
(1)
Natural Language Processing
(1)
Applications · Natural Language Processing
(1)
Applications · Data Science & Analytics
(1)
Architectures
(1)
Core Methods
(1)
Learning Types
(1)
Models
(1)
Processing
(1)
Techniques
(1)
Keywords
attention mechanism
(1)
temporal reasoning
(1)
multimodal learning
(1)
video understanding
(1)
cross-modal retrieval
(1)
sparse attention
(1)
fine-grained understanding
(1)
video-language model
(1)
user preference modeling
(1)
user preference
(1)
session-based recommendation
(1)
reasoning path
(1)
video grounding
(1)
dense video captioning
(1)
temporal video grounding
(1)
large language model
(1)
temporal boundary
(1)
item embedding
(1)
audio-visual question answering
(1)
multimodal llm
(1)
Papers
Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification
ACL 2026
Modularized Self-Reflected Video Reasoner for Multimodal LLM with Application to Video Question Answering
ICML 2025
VTimeLLM: Empower LLM to Grasp Video Moments
CVPR 2024
Dual Sparse Attention Network For Session-based Recommendation
AAAI 2021