Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published May 7 • 237
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System Paper • 2604.14125 • Published Apr 15 • 21
Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning Paper • 2604.06079 • Published Apr 7 • 7
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published Apr 2 • 509
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 329
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents Paper • 2604.06132 • Published Apr 7 • 122
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Paper • 2603.28032 • Published Mar 30 • 344
HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions Paper • 2603.15612 • Published Mar 16 • 153
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models Paper • 2602.22859 • Published Feb 26 • 150