Yi Chang

7 papers Jilin University

• Accelerated Vertical Federated Adversarial Learning through Decoupling Layer-Wise Dependencies
• Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning
• Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning
• InstructFlow: Adaptive Symbolic Constraint-Guided Code Generation for Long-Horizon Planning
• LLM Meeting Decision Trees on Tabular Data
• StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization
• Tackling Continual Offline RL through Selective Weights Activation on Aligned Spaces