Liam Thompson
liamthompson1994
AI & ML interests
None yet
Recent Activity
upvoted a paper 23 days ago
Predicting Mergeability of Parameter-Efficient Fine-Tuning Updates upvoted a paper about 1 month ago
TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning upvoted a paper about 1 month ago
Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response SimplexOrganizations
None yet