AI.info

Usman Naseem

Explore Usman Naseem on AI.info.

• Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness
• From Native Memes to Global Moderation: Cross-Cultural Evaluation of Vision-Language Models for Hateful Meme Detection
• Health-ORSC-Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context