AmongUs: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems
ziyuan yang
ziyuanyang86
AI & ML interests
None yet
Recent Activity
published a model 3 days ago
ziyuanyang86/llama3_grpo updated a model 12 days ago
ziyuanyang86/4b_prefixwrong published a model 12 days ago
ziyuanyang86/4b_prefixwrongOrganizations
None yet
models 25
ziyuanyang86/llama3_grpo
Updated
ziyuanyang86/4b_prefixwrong
4B • Updated • 37
ziyuanyang86/1.7b_prefixwrong
2B • Updated • 25
ziyuanyang86/4b_wrongbox
4B • Updated • 47
ziyuanyang86/1.7b_wrongbox
2B • Updated • 35
ziyuanyang86/1.7b_misconcept
2B • Updated • 31
ziyuanyang86/4b_misconcept
4B • Updated • 35
ziyuanyang86/4b_reason_llm
4B • Updated • 28
ziyuanyang86/4b_diversity_llm
4B • Updated • 33
ziyuanyang86/4b_sft
Text Generation • 4B • Updated • 8