🔄 In a Training Loop

xuluxin

2041Xu

13

·

AI & ML interests

None yet

Recent Activity

authored a paper 4 days ago

PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails

authored a paper 4 days ago

$π$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

authored a paper 4 days ago

AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning

View all activity

Organizations

2041Xu 's papers 5

arxiv:2607.05910

arxiv:2605.14678

arxiv:2601.18631

arxiv:2511.04328

arxiv:2502.09990