Kishan
kishanpb
AI & ML interests
None yet
Recent Activity
authored
a paper
3 days ago
Guided Self-Evolving LLMs with Minimal Human Supervision
authored
a paper
3 days ago
Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning
authored
a paper
2 months ago
Every Question Has Its Own Value: Reinforcement Learning with Explicit
Human Values
Organizations
None yet