arxiv:2606.19162
🤝 Open to Collab
Felix Friedrich
felfri
AI & ML interests
Multimodal AI; Post-training/Inference; AI Safety; AI Alignment
Recent Activity
authored a paper about 9 hours ago
No Safe Dose: How Training Data Drives Unsafe Image Generation upvoted a paper 1 day ago
LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking upvoted a paper 1 day ago
No Safe Dose: How Training Data Drives Unsafe Image GenerationOrganizations
arxiv:2606.09809
arxiv:2605.28137
arxiv:2604.15149
arxiv:2601.10553
arxiv:2512.07522
arxiv:2511.05613
arxiv:2510.18184
arxiv:2506.19382
arxiv:2506.16679
arxiv:2506.15787
arxiv:2506.09827
arxiv:2505.20033
arxiv:2503.05731
arxiv:2501.10057
arxiv:2412.15035
arxiv:2411.07122
arxiv:2406.05113
arxiv:2404.08676
arxiv:2404.00399
arxiv:2401.16092
arxiv:2311.16711
arxiv:2305.18398
arxiv:2305.15296
arxiv:2303.09289
arxiv:2302.10893
arxiv:2301.12247
arxiv:2212.06013
arxiv:2210.10332
arxiv:2209.08891
arxiv:2209.07341
arxiv:2203.03668
arxiv:2110.02058
