#THE
共找到 3467 篇相关文章
评估将会中断
We're good at evaluating the models we have。We're much worse at evaluating the models we're about to build — especially
GitHub 正在调查 TeamPCP 声称约 4,000 个内部存储库遭到破坏
GitHub on Tuesday said it's investigating unauthorized access to its internal repositories after the notorious threat ac
基于平坦度的理论最优量化
18800v1 Announce Type: new Abstract: Post-training quantization has emerged as a widely adopted technique for compressin
通过全环路变压器简单地稳定环路
18797v1 Announce Type: new Abstract: Scaling model performance typically requires increasing model size。
用于变压器模型压缩的鲁棒基础样条解耦
18794v1 Announce Type: new Abstract: Decoupling is a powerful modeling paradigm for representing multivariate functions
维度平衡提高大规模时空预测性能
18793v1 Announce Type: new Abstract: Accurate spatiotemporal pattern analysis is critical in fields such as urban traffi
干扰感知多任务忘却
19042v1 Announce Type: new Abstract: Machine unlearning aims to remove the contribution of designated training data from
AgentNLQ:自然语言到 SQL 的通用代理
arXiv:2605.19010v1 Announce Type: new Abstract: Natural language to SQL (NL2SQL) conversion is an important problem for
实施文档 AI:生产中 OCR 和 LLM 管道的微服务架构
arXiv:2605.18818v1 Announce Type: new Abstract: Academic research tends to focus on new models for document understandin