When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels Paper • 2605.06652 • Published 5 days ago • 4
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published 5 days ago • 66
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation Paper • 2604.28196 • Published 12 days ago • 70
ATTN-FIQA: Interpretable Attention-based Face Image Quality Assessment with Vision Transformers Paper • 2604.22841 • Published 21 days ago • 5
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 324
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published Apr 2 • 501
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published Apr 3 • 627
MemRerank: Preference Memory for Personalized Product Reranking Paper • 2603.29247 • Published Mar 31 • 5
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Paper • 2603.28032 • Published Mar 30 • 341
HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions Paper • 2603.15612 • Published Mar 16 • 153