Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments Paper • 2609.04148 • Published 6 days ago • 290
Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement Paper • 2608.31046 • Published 9 days ago • 144
LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation Paper • 2608.30935 • Published 9 days ago • 32
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers Paper • 2609.01343 • Published 8 days ago • 99