Jimin Zhuang
3 papers · 2025–2025 · 2 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
🌉
Interdisciplinary Bridge · Silver
Top co-authors
Research topics
Keywords
video understanding
(2)
visual question answering
(1)
audio-visual learning
(1)
semantic information
(1)
multimodal large language model
(1)
visual token
(1)
frame rate
(1)
visual language model
(1)
audio-visual interaction
(1)
large language model
(1)
video comprehension
(1)
audio-centric video understanding
(1)
step-by-step solution
(1)
low-frame-rate inference
(1)
audio-visual llm
(1)
process direct preference optimization (pdpo)
(1)
reasoning-intensive dataset
(1)
rivabench
(1)
benchmark evaluation
(1)
zero-shot synthetic video detection
(1)