Xiaoyu Wen's picture

Open to Work

3

Xiaoyu Wen

XiaoyuWen

·

AI & ML interests

None yet

Recent Activity

updated a dataset 6 days ago

XiaoyuWen/PIA-Persona-Dataset

updated a collection 6 days ago

updated a collection 6 days ago

View all activity

Organizations

updated a dataset 6 days ago

XiaoyuWen/PIA-Persona-Dataset

Viewer • Updated 6 days ago • 35 • 32

updated a collection 6 days ago

PIA

ICML2026 paper: "Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment" • 2 items • Updated 6 days ago • 1

upvoted a collection 6 days ago

PIA

ICML2026 paper: "Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment" • 2 items • Updated 6 days ago • 1

updated a model 6 days ago

XiaoyuWen/PIA

Updated 6 days ago

published a model 6 days ago

XiaoyuWen/PIA

Updated 6 days ago

published a dataset 6 days ago

XiaoyuWen/PIA-Persona-Dataset

Viewer • Updated 6 days ago • 35 • 32

updated a collection 3 months ago

MAGIC

ICML2026 paper: "MAGIC: A Co-Evolving Attacker–Defender Adversarial Game for Robust LLM Safety" • 4 items • Updated 6 days ago • 3

upvoted a collection 3 months ago

MAGIC

ICML2026 paper: "MAGIC: A Co-Evolving Attacker–Defender Adversarial Game for Robust LLM Safety" • 4 items • Updated 6 days ago • 3

updated a collection 3 months ago

MAGIC

ICML2026 paper: "MAGIC: A Co-Evolving Attacker–Defender Adversarial Game for Robust LLM Safety" • 4 items • Updated 6 days ago • 3

upvoted a paper 3 months ago

MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety

Paper • 2602.01539 • Published Feb 2 • 1

updated 4 models 3 months ago

XiaoyuWen/MAGIC-Llama3.1-8B-Instruct

Text Generation • Updated Feb 4 • 4

XiaoyuWen/MAGIC-Qwen2.5-7B-Instruct

Text Generation • 8B • Updated Feb 4 • 7 • • 2

XiaoyuWen/MAGIC-Qwen2.5-14B-Instruct

Text Generation • Updated Feb 4 • 8 • 1

XiaoyuWen/MAGIC

Text Generation • Updated Feb 4 • 1

updated a dataset 3 months ago

XiaoyuWen/MAGIC-Attack-Pool-Benchmark

Preview • Updated Feb 4 • 3

published a dataset 3 months ago

XiaoyuWen/MAGIC-Attack-Pool-Benchmark

Preview • Updated Feb 4 • 3

published a model 3 months ago

XiaoyuWen/MAGIC

Text Generation • Updated Feb 4 • 1