No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping
Paper • 2509.21880 • Published • 54 •
3
Thanh-Long V. Le
bltnynk
AI & ML interests
None yet
Recent Activity
authored a paper about 2 hours ago
FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching upvoted a paper about 9 hours ago
XFlow: A Workflow Model for Instruction-Guided Lesion Segmentation in Chest X-raysOrganizations
None yet
commented a
paper about 1 year ago
Further release and details
7
#1 opened almost 2 years ago
by 
Leon-Leee