One Token to Fool LLM-as-a-Judge
Paper • 2507.08794 • Published • 32
Haolin Liu
lhl616
AI & ML interests
None yet
Recent Activity
upvoted a paper about 5 hours ago
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling upvoted a paper 26 days ago
Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization upvoted a paper 3 months ago
Training Data Efficiency in Multimodal Process Reward ModelsOrganizations
None yet
authored a
paper 10 months ago