FT-AOs and paired taboo subjects on Qwen3-8B, used in arXiv:2607.23379. Base AO recipe: Karvonen et al. 2025 (arXiv:2512.15674).
Tatiana Gaintseva
Atmyre
·
AI & ML interests
Computer vision, diffusion models, explainability, adversarial robustness
Recent Activity
updated a collection about 1 month ago
AO Anti-Reading updated a collection about 1 month ago
AO Anti-Reading updated a model about 1 month ago
Atmyre/qwen3-8b-ao-strict-moon-c0p50Organizations
models 41
Atmyre/qwen3-8b-ao-strict-moon-c0p50
Text Generation • Updated • 13
Atmyre/qwen3-8b-ao-strict-leaf-c0p50
Text Generation • Updated • 13
Atmyre/qwen3-8b-taboo-strict-wave-c1p00
Updated • 14
Atmyre/qwen3-8b-taboo-strict-wave-c0p50
Updated • 14
Atmyre/qwen3-8b-taboo-strict-moon-c1p00
Updated • 18
Atmyre/qwen3-8b-taboo-strict-moon-c0p50
Updated • 18
Atmyre/qwen3-8b-taboo-strict-leaf-c1p00
Updated • 16
Atmyre/qwen3-8b-taboo-strict-leaf-c0p50
Updated • 18
Atmyre/qwen3-8b-taboo-strict-flag-c1p00
Updated • 14
Atmyre/qwen3-8b-taboo-strict-flag-c0p50
Updated • 16
datasets 0
None public yet