Your LR Schedule May Not Be Principled: Effective Learning Rate Scheduling in Weight-Normalized Training Paper • 2610.40362 • Published 21 days ago • 9
PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews Paper • 2610.21046 • Published Oct 15 • 18
SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum Paper • 2610.26824 • Published about 1 month ago • 21
Speculative Forcing for Efficient Autoregressive Video Generation Paper • 2610.22347 • Published Oct 15 • 77
LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets Paper • 2610.09872 • Published Oct 7 • 27
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published Sep 27 • 82
FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasets Paper • 2609.35770 • Published Sep 28 • 5
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression Paper • 2609.36322 • Published Sep 28 • 31
Redesign Mixture-of-Experts Routers with Manifold Power Iteration Paper • 2606.12397 • Published Jun 10 • 43
Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings Paper • 2606.07502 • Published Jun 5 • 47
SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Paper • 2602.02472 • Published Feb 2 • 21
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss Paper • 2512.23447 • Published Dec 29, 2025 • 62