Anisha Saha

Identifiers

• name variant Anisha Saha 0.60 · backfill

Papers (2)

1. MuPHI: Learning Implicit Multimodal Harm Reasoning via Semantically Grounded Reward Optimization cs.AI · 2026 · author #1
2. System-Mediated Attention Imbalances Make Vision-Language Models Say Yes cs.CL · 2026 · author #3

Mentions

• 2605.29951 #1 · arxiv_oai · confidence 0.70 Anisha Saha

Frequent Coauthors

• Varsha Suresh 2 shared papers
• Vera Demberg 2 shared papers
• Michael Hahn 1 shared papers
• Sophia Wiedmann 1 shared papers
• Teodora Kamova 1 shared papers
• Timothy Hospedales 1 shared papers
• Tsan Tsai Chan 1 shared papers