Teodora Kamova
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
AI×1NLP×1ML×1Multimedia×1
Frequent co-authors
Research Timeline
2026
MuPHI: Learning Implicit Multimodal Harm Reasoning via Semantically Grounded Reward Optimization
The paper introduces MuPHI, a dataset and MuPHIRM, a reasoning-augmented training framework, to improve Vision-Language Models' ability to detect and reason about subtle, context-dependent multimodal harm.
Highlighted terms show continued research focus across papers
Papers
cs.AIcs.CLcs.LGRecentMay 28, 2026
MuPHI: Learning Implicit Multimodal Harm Reasoning via Semantically Grounded Reward Optimization
Anisha Saha, Varsha Suresh, Teodora Kamova, Sophia Wiedmann +2 more
The paper introduces MuPHI, a dataset and MuPHIRM, a reasoning-augmented training framework, to improve Vision-Language Models' ability to detect and reason about subtle, context-dependent multimodal…
View →