流式视频压缩新思路，用集合思维大幅削减token冗余，兼顾效率与质量。
arXiv:2608.01169v1 Announce Type: new Abstract: Streaming VideoLLMs process frames causally while visual tokens grow continuously, making compression …
少数据也能训出强安全大模型，这项研究用最少Token实现领域自适应预训练，大幅降低算力门槛。
arXiv:2507.02964v2 Announce Type: replace-cross Abstract: The increasing scale of AI workloads demands High-Performance Computing (HPC) infrastructure…
开源CLI工具ctx，本地搜索编码代理历史会话，token效率提升50倍
Hi HN, we posted here back in April and the most common request was to make the source code public. As of today, ctx is now open-source: https://githu…
斯坦福团队构建高质量金融披露数据集，兼顾布局忠实与token高效，为NLP预训练提供新基准。
arXiv:2606.18192v1 Announce Type: new Abstract: As high-quality public web corpora become increasingly exhausted, clean long-context documents have be…
用最少token检测LLM API行为变化，这项研究或能大幅降低监控成本与延迟
arXiv:2602.11083v3 Announce Type: replace Abstract: Remote change detection in LLMs is a difficult problem. Existing methods are either too expensive …
节省20,000 tokens的代码库索引器，让AI编程工具更省钱高效。
Article URL: https://github.com/leogong99/codepulse Comments URL: https://news.ycombinator.com/item?id=48319172 Points: 2 # Comments: 0