Yibo Peng

pybbb

·

https://pppyb.github.io/

AI & ML interests

None yet

Recent Activity

submitted a paper about 12 hours ago

SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation

authored a paper 2 days ago

MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning

authored a paper 2 days ago

When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?

View all activity

Organizations

Papers 4

arxiv:2608.21500

arxiv:2602.22426

arxiv:2510.17862

arxiv:2506.00555

models 3

pybbb/Qwen3.6-27B-SecOPD

Image-Text-to-Text • 28B • Updated 13 days ago • 180

pybbb/Llama-3.1-8B-Instruct-anti-dpo-sizhe

Text Generation • 8B • Updated Mar 5 • 16 •

pybbb/Llama-3.1-8B-Instruct-anti-dpo

8B • Updated Feb 27 • 3

datasets 2

pybbb/simpleocr

Viewer • Updated Feb 18 • 31.2k • 23

pybbb/OCR_ONLY

Preview • Updated Jun 28, 2025 • 82