arxiv:2606.30562
Disen Lan
landisen
AI & ML interests
None yet
Recent Activity
upvoted a paper about 7 hours ago
T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks upvoted a paper 9 days ago
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers upvoted a paper 15 days ago
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness EvolutionOrganizations
models 0
None public yet
datasets 0
None public yet