Yikun Ban

UniARM: Towards a Unified Autoregressive Reward Model for Multi-Objective Test-Time Alignment

FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits

LLMBoost: Make Large Language Models Stronger with Boosting

BoMM: Multi-Modality Large-Small Model Bidirectional Collaboration

sNet: Not All Edges Matter Equally in Temporal Link Prediction

Towards Scalable Distance-Enhanced Graph Neural Network

T-POP: Test-Time Personalization with Online Preference Feedback

Reinforcement Reward Model with Policy Feedback

Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization

Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning

Multi-modal Prompt Learning Empowers Graph Neural Networks with Semantic Knowledge