arxiv:2609.37868
Sihwan Park
sihwanpark
AI & ML interests
None yet
Recent Activity
submitted a paper 1 day ago
KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization authored a paper 2 days ago
Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR authored a paper 2 days ago
LANTERN++: Enhanced Relaxed Speculative Decoding with Static Tree
Drafting for Visual Auto-regressive ModelsOrganizations
None yet