Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published 8 days ago • 181
ESARBench: A Benchmark for Agentic UAV Embodied Search and Rescue Paper • 2605.01371 • Published 13 days ago • 6
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model Paper • 2604.20796 • Published 23 days ago • 240
CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models Paper • 2604.04780 • Published Apr 6 • 10
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published Apr 2 • 501
MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping Paper • 2604.08364 • Published Apr 9 • 101
SciLT: Long-Tailed Classification in Scientific Image Domains Paper • 2604.03687 • Published Apr 4 • 8