PPL
Chen Zhang
Papers (4)
Learning to Adapt SFT Data for Better Reasoning GeneralizationOmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and RegularizationDRL-STAF: A Deep Reinforcement Learning Framework for State-Aware Forecasting of Complex Multivariate Hidden Markov ProcessesPruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning