Mi Zhang

Reading Recognition in the Wild

SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning

SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression

$\text{D}_{2}\text{O}$: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models

ECG Instruction Tuning on Multimodal LLMs for Report Generation: Benchmark and Evaluation

GPT-FL: Generative Pre-trained Model-Assisted Federated Learning

FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things