Yunjian Xu
3 papers · 2024–2025 · 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 · Bronze
Top co-authors
Research topics
Keywords
representation learning
(1)
offline reinforcement learning
(1)
direct preference optimization
(1)
preference alignment
(1)
diffusion model
(1)
generalization capability
(1)
vision-language model
(1)
hallucination mitigation
(1)
safe offline reinforcement learning
(1)
large vision-language model
(1)
out-of-distribution problem
(1)
state perturbation
(1)
on-policy alignment
(1)
model-based prediction
(1)
q-supervised contrastive
(1)
state decoupling
(1)
Papers
Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
CVPR 2025
Q-Supervised Contrastive Representation: A State Decoupling Framework for Safe Offline Reinforcement Learning
ICML 2025
DMBP: Diffusion model-based predictor for robust offline reinforcement learning against state observation perturbations
ICLR 2024