Tong Xu

4

Papers

889

Total Citations

Papers (4)

Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation

Multi-Branch Self-Drafting for LLM Inference Acceleration

FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning