Zenghui Sun
3 papers · 2025–2026 · 3 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
image captioning
(3)
visual question answering
(1)
multimodal interaction
(1)
information loss
(1)
large multimodal model
(1)
large vision-language model
(1)
multi-granularity segmentation
(1)
modality conversion
(1)
instruction-guided learning
(1)
segmentation and captioning
(1)
reinforcement learning
(1)
cross-modal identity mapping
(1)
Papers
Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning
CVPR 2026
Instruction-guided Multi-Granularity Segmentation and Captioning with Large Multimodal Model
AAAI 2025
INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling
ICCV 2025