Layla Khoury
layla-k
ยท
AI & ML interests
multimodal RAG, subgraph mining, network science
Recent Activity
upvoted a paper about 21 hours ago
PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning upvoted a paper 2 days ago
Rethinking Relative Policy Differences Transfer of On-Policy Distillation upvoted a paper 4 days ago
On-Policy Distillation with Negative-Policy RolloutsOrganizations
None yet