Author

Manisha Mukherjee

h-index 3 View on Semantic Scholar

We have 2 of 21 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Apr 2026

Reward Design for Physical Reasoning in Vision-Language Models

It is found that external rewards drive most of the accuracy gains, while preserving more coherent reasoning when rewarded for reasoning tokens, while preserving more coherent reasoning when rewarded for reasoning tokens through internal attention rewards.

Derek Lilienthal, Manisha Mukherjee, Sameera Horawalavithana · arXiv.org · 1 citation

Book Open access Jul 2026

SOSecure: The Wisdom of the Crowd for Safer AI-Generated Code

SOSecure is introduced, a Retrieval- Augmented Generation (RAG) system that leverages the collective security expertise found in SO discussions to improve the security of LLM-generated code, and builds a security-focused knowledge base by extracting SO answers and comments that explicitly identify vulnerabilities.

Manisha Mukherjee, Vincent J. Hellendoorn · AIware · 0 citations