AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition Paper • 2607.02271 • Published 6 days ago • 15
MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding Paper • 2510.23479 • Published Oct 27, 2025 • 18
LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs Paper • 2603.19217 • Published Mar 19 • 29
RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution Paper • 2605.21195 • Published May 20 • 19
Taming LLMs by Scaling Learning Rates with Gradient Grouping Paper • 2506.01049 • Published Jun 1, 2025 • 39