4 papers
MuPHI: Learning Implicit Multimodal Harm Reasoning via Semantically Grounded Reward Optimization
Anisha Saha, Varsha Suresh, Teodora Kamova +3
Understanding how harm emerges from interaction between otherwise benign image-text pairs requires intent-aware cross-modal reasoning beyond surface-level features. Existing vision…
: Multi-modal Multi-span Medical Question Answering
Anisha Saha, Vaibhav Rathore, Abhisek Tiwari +3
The growing adoption of AI in healthcare, particularly in preventive care, highlights the critical need for accessibility and precision in Medical Question Answering (MedQA). In re…
System-Mediated Attention Imbalances Make Vision-Language Models Say Yes
Tsan Tsai Chan, Varsha Suresh, Anisha Saha +2
Vision-language model (VLM) hallucination is commonly linked to imbalanced allocation of attention across input modalities: system, image and text. However, existing mitigation str…
MUStReason: A Benchmark for Diagnosing Pragmatic Reasoning in Video-LMs for Multimodal Sarcasm Detection
Anisha Saha, Varsha Suresh, Timothy Hospedales +1
Sarcasm is a specific type of irony which involves discerning what is said from what is meant. Detecting sarcasm depends not only on the literal content of an utterance but also on…