LEV: Thinking Fast and Deep with Looped Decision Models Paper • 2610.20951 • Published 12 days ago • 107
Learning to Read Out: Unembedding Dynamics in Language Model Pretraining Paper • 2610.21025 • Published 12 days ago • 10
SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum Paper • 2610.26824 • Published 7 days ago • 89
LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation Paper • 2610.19975 • Published 12 days ago • 82
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression Paper • 2609.36322 • Published 28 days ago • 120
CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs Paper • 2609.31957 • Published 30 days ago • 7
Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings Paper • 2606.07502 • Published Jun 5 • 100
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss Paper • 2512.23447 • Published Dec 29, 2025 • 100