AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security Paper • 2605.29801 • Published 11 days ago • 142
deqing/convergent-llama-300M-muon-6digit-addition_6digit_llama Text Generation • 0.3B • Updated 4 days ago • 1.32k • 1
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published May 7 • 233
Geometric Phase Transition Enables Extreme Hippocampal Memory Capacity Paper • 2605.17199 • Published 23 days ago • 6
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution Paper • 2605.18401 • Published 21 days ago • 126
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Paper • 2604.24763 • Published Apr 27 • 71