arxiv:2510.01353
Darshan Deshpande
DarshanDeshpande
AI & ML interests
Explainability, Robustness, Evaluations
Recent Activity
new activity 10 days ago
PatronusAI/world_model_corpus:Add reinforcement-learning task category, paper and GitHub links submitted a paper 11 days ago
Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RLOrganizations
models 9
DarshanDeshpande/sherllama3_ia3
Updated
DarshanDeshpande/gemma_2b_oasst1_reward_model
Updated • 4
DarshanDeshpande/gemma_2b_oasst1_ppo_model
Reinforcement Learning • Updated • 2
DarshanDeshpande/distilbert_eli5_reward_model
Text Classification • 67M • Updated • 4
DarshanDeshpande/distilbert_social_reasoning_reward_model
Text Classification • 67M • Updated • 3
DarshanDeshpande/gemma_2b_social_reasoning_reward_model
Updated • 1
DarshanDeshpande/gemma_2b_anthropic_reward_model
Updated
DarshanDeshpande/gemma-2b-lora-commonsense-qa
Updated
DarshanDeshpande/marathi-distilbert
Fill-Mask • Updated • 24 • 3
datasets 0
None public yet