Yishuo Cai
5 papers · 2024–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (4) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (11) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
EMNLP (2)
ACL (1)
CVPR (1)
ICML (1)
Top co-authors
Keywords
multimodal large language model
(2)
benchmark evaluation
(1)
image generation
(1)
preference learning
(1)
multimodal learning
(1)
image captioning
(1)
harmful content
(1)
safety alignment
(1)
visual reconstruction
(1)
backdoor attack
(1)
adversarial defense
(1)
synthetic datum
(1)
text-to-image model
(1)
vision-language model
(1)
hallucination mitigation
(1)
jailbreak attack
(1)
hallucination detection
(1)
token-level detection
(1)
large language model
(1)
image recaptioning
(1)
Papers
MHALO: Evaluating MLLMs as Fine-grained Hallucination Detectors
ACL 2025
RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction
EMNLP 2025
Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
CVPR 2024
Course-Correction: Safety Alignment Using Synthetic Preferences
EMNLP 2024
Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation
ICML 2024