Guoshun Nan

7

Papers

14

Total Citations

Papers (7)

Advancing Expert Specialization for Better MoE

Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models

VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-based Group Relative Policy Optimization

From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning

DocMSU: A Comprehensive Benchmark for Document-Level Multimodal Sarcasm Understanding

Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks

Uncovering What Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly