POLCA: Stochastic Generative Optimization with LLM
Paper • 2603.14769 • Published • 22
Xuanfei Ren
xuanfeiren
AI & ML interests
RL and LLM
Recent Activity
upvoted a paper 13 days ago
Provably Learning from Language Feedback upvoted a paper 13 days ago
Understanding the Challenges in Iterative Generative Optimization with LLMs upvoted a paper 16 days ago
Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov StatesOrganizations
None yet
authored a
paper 22 days ago