Unverified50% confidenceFactExact time
EfficientNet 系列由 Google Brain 在 2019 年提出，核心创新是复合缩放，从 B0 到 B7 参数从 5.3M 增长到 66M，Top-1 精度从 77.1% 提升到 84.3%
1
Sources
50%
Confidence
Long-term
Relevance
8/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGoogle Brain团队于2022年系统记录了涌现能力现象，发现某些能力在模型达到特定规模前几乎为零，之后突然跃升74% similarUnverifiedGoogle DeepMind研究表明，涌现能力表现为非线性的相变特征，模型参数量从10B增长到100B过程中某些复杂推理能力会突然跃升69% similarUnverifiedIn Google Brain's 2020 ViT paper, it was noted that ViT trained from scratch on ImageNet-1K (1.28 million images) underperforms CNNs of equivalent scale, but begins to surpass CNNs when pre-training data is scaled to ImageNet-21K (14 million images) or JFT-300M (300 million images)68% similarUnverifiedMedIQ多智能体系统最终达到57%准确率，摘要智能体带来约5%提升，而拥有全部前置信息的Oracle上限为66%67% similarUnverified2023年MIT与Google的联合研究表明，当子任务存在明确完成标准时，智能体的自我纠错效率可提升40%以上63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/810814API
curl https://kongchang.com/api/v1/knowledge/claims/810814MCP
get_claim(id=810814)