Rui Yan

4 papers Nanjing University of Science and Technology

• DAPO : Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage-Based Policy Optimization
• PolarQuant: Leveraging Polar Transformation for Key Cache Quantization and Decoding Acceleration
• Vision-centric Token Compression in Large Language Model
• You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM