Your LR Schedule May Not Be Principled: Effective Learning Rate Scheduling in Weight-Normalized Training Paper • 2610.40362 • Published 4 days ago • 8
Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models Paper • 2610.22428 • Published 18 days ago • 17
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence Paper • 2609.17488 • Published Sep 15 • 286
SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum Paper • 2610.26824 • Published 14 days ago • 36
RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution Paper • 2610.15772 • Published 22 days ago • 8
ClawLoop: Self-Improving Agents via Harness-Native Training Loop Paper • 2610.14118 • Published 24 days ago • 34
TimeRSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models Paper • 2610.19725 • Published 18 days ago • 5
Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine Paper • 2610.22192 • Published 18 days ago • 38
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses Paper • 2610.23839 • Published 17 days ago • 20
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression Paper • 2609.36322 • Published Sep 28 • 40
ICA Lens: Interpreting Language Models Without Training Another Dictionary Paper • 2606.11722 • Published Jun 10 • 11
Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions Paper • 2606.09076 • Published Jun 8 • 62
Redesign Mixture-of-Experts Routers with Manifold Power Iteration Paper • 2606.12397 • Published Jun 10 • 50
Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings Paper • 2606.07502 • Published Jun 5 • 55
SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning Paper • 2602.02472 • Published Feb 2 • 24
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss Paper • 2512.23447 • Published Dec 29, 2025 • 67