Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts Paper • 2610.01153 • Published 6 days ago • 16
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 6 days ago • 262
Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models Paper • 2610.03665 • Published 5 days ago • 52
AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation Paper • 2609.38142 • Published 8 days ago • 12
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence Paper • 2609.34563 • Published 9 days ago • 216