利用越狱图像(Jailbreak Images)攻击多模态融合模型
论文Gradient-based Jailbreak Images for Multimodal Fusion...
Read MoreExPLoRA:实现视觉Transformer(ViT)在不完全解冻模型的情况下,继续在新的目标领域进行自监督学习
论文《ExPLoRA: Parameter-Efficient Extended Pre-Training t...
Read More诺奖得主Geoffrey Hinton的一篇老论文,关于知识蒸馏(Distilling)
Distilling the Knowledge in a Neural Network是Geoffrey H...
Read MoreAOI(Augmented Object Intelligence):增强对象智能
空间计算(spatial computing)和人工智能(AI)的进展为扩展现实(extended reali...
Read More约束生成策略优化(CGPO)框架解决基于人类反馈强化学习(RLHF)在多任务学习(MTL)中的局限性
论文The Perfect Blend: Redefining RLHF with Mixture of Ju...
Read MoreCoT(Chain of Thought)在数学和符号推理任务中表现突出
论文To CoT or not to CoT? Chain-of-thought helps mainly o...
Read More识别和评估大型语言模型(LLM)在医疗健康领域的潜在偏见和健康不公平
论文A toolbox for surfacing health equity harms and biase...
Read More












