4 Commits

Author SHA1 Message Date
dongdongunique
bd1cd2e1b1 Complete Phase 2: SOTA LLM Testing
- Add EvoSynth vs X-Teaming comparison table with 20 models
- EvoSynth achieves 98.8% avg ASR vs X-Teaming 87.9% (+10.9% improvement)
- 100% ASR on 17 out of 20 evaluated models
- Add arxiv/ folder to .gitignore
2026-02-04 13:53:11 +08:00
dongdongunique
20e8068b7b 📝 Add diagram.pdf to .gitignore 2025-12-10 15:09:58 +08:00
dongdongunique
e36eaa0a61 📝 Update .gitignore 2025-12-10 15:04:01 +08:00
dongdongunique
a5e5185c10 Add .gitignore 2025-12-10 03:17:39 +08:00