VL-BEiT: Generative Vision-Language Pretraining

VL-BEiT:生成式视觉-语言预训练.

Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition

理解领悟能力、U型尺度定律和涌现能力的统一视角.

YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

YOLOv9:通过可编程梯度信息学习想学习的内容.

LoRA+: Efficient Low Rank Adaptation of Large Models

LoRA+:大模型的高效低秩微调.

Video generation models as world simulators

视频生成模型作为世界模拟器.

Enhancing Zero-shot Counting via Language-guided Exemplar Learning

通过语言引导的模板学习增强零样本计数.