Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published 10 days ago • 182
Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains Paper • 2604.24902 • Published 20 days ago • 2
Heterogeneous Scientific Foundation Model Collaboration Paper • 2604.27351 • Published 17 days ago • 213
DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off Paper • 2604.13902 • Published Apr 15 • 62
Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference Paper • 2604.07394 • Published Apr 8 • 16
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published Apr 2 • 503
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 324
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models Paper • 2604.08546 • Published Apr 9 • 115
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Paper • 2603.28032 • Published Mar 30 • 342