Ruiming Tang

6

Papers

114

Total Citations

Papers (6)

ToolACE: Winning the Points of LLM Function Calling

MTRec: Learning to Align with User Preferences via Mental Reward Models

NeurIPS 2025arXiv

D3: A Methodological Exploration of Domain Division, Modeling, and Balance in Multi-Domain Recommendations

On Effective Scheduling of Model-based Reinforcement Learning

Optimal Transport for Treatment Effect Estimation

REASONER: An Explainable Recommendation Dataset with Comprehensive Labeling Ground Truths