已发表成果:
WOK 论文 102 篇;中文核心 14 篇;其它论文 3 篇;
Unbiased news recommendation model time and content
Who To Align With: Feedback-Oriented Multi-Modal Alignment in Recommendation Systems
Improving Multi-modal Recommender Systems by Denoising and Aligning Multi-modal Content and User Feedback
RHO-1: Not All Tokens Are What You Need
Federated Learning with Extremely Noisy Clients via Negative Distillation
Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models
Leveraging Dynamic and HeterogeneousWorkload Knowledge to Boost the Performance of Index Advisors
APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning
Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models
TRAP: Tailored Robustness Assessment for Index Advisors via Adversarial Perturbation
THINK-ON-GRAPH: DEEP AND RESPONSIBLE REASONING OF LARGE LANGUAGE MODEL ON KNOWLEDGE GRAPH
Compound-Protein Interaction Prediction with Sparse Perturbation-Aware Attention
Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models