Darshan Deshpande
DarshanDeshpande
AI & ML interests
Explainability, Robustness, Evaluations
Recent Activity
liked
a dataset
1 day ago
PatronusAI/trace-dataset
upvoted
a
paper
2 days ago
Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
submitted
a paper
2 days ago
Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis