Guangyu Yang
4 papers · 2024–2026 · 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
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
Top co-authors
Research topics
Keywords
multi-view clustering
(1)
adversarial robustness
(1)
direct preference optimization
(1)
neural machine translation
(1)
probabilistic model
(1)
large multimodal model
(1)
retrieval-augmented generation
(1)
cross-domain generalization
(1)
retrieval augmentation
(1)
minimum bayes risk
(1)
tensor regression
(1)
label learning
(1)
anchor graph
(1)
multilingual large language model
(1)
jailbreak detection
(1)
hateful meme detection
(1)
large language model
(1)
safety-utility trade-off
(1)
jailbreak prevention
(1)
Papers
Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models
ACL 2026
Tensorized Label Learning via Balanced Tensor Regression
AAAI 2026
Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection
EMNLP 2025
Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding
NAACL 2024