arxiv:2506.04142
Shangqing Tu
tsq2000
·
AI & ML interests
None yet
Recent Activity
authored
a paper
1 day ago
Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis
authored
a paper
1 day ago
MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in
Videos
upvoted
a
paper
2 days ago
Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis
Organizations
Papers
10
datasets
0
None public yet