arxiv:2510.01353
Darshan Deshpande
DarshanDeshpande
AI & ML interests
Explainability, Robustness, Evaluations
Recent Activity
liked
a dataset
about 6 hours ago
PatronusAI/trace-dataset
submitted
a paper
1 day ago
Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
Organizations
models
9
DarshanDeshpande/sherllama3_ia3
Updated
DarshanDeshpande/gemma_2b_oasst1_reward_model
Updated
•
1
DarshanDeshpande/gemma_2b_oasst1_ppo_model
Reinforcement Learning
•
Updated
DarshanDeshpande/distilbert_eli5_reward_model
Text Classification
•
67M
•
Updated
•
3
DarshanDeshpande/distilbert_social_reasoning_reward_model
Text Classification
•
67M
•
Updated
•
4
DarshanDeshpande/gemma_2b_social_reasoning_reward_model
Updated
•
3
DarshanDeshpande/gemma_2b_anthropic_reward_model
Updated
DarshanDeshpande/gemma-2b-lora-commonsense-qa
Updated
DarshanDeshpande/marathi-distilbert
Fill-Mask
•
Updated
•
3
•
3
datasets
0
None public yet