注册并分享邀请链接,可获得视频播放与邀请奖励。

与「LIVEVE」相关的搜索结果

LIVEVE 贴吧
一个关键词就是一个贴吧,路径全站唯一。
创建贴吧
用户
未找到
包含 LIVEVE 的内容
RAG system that skips HTML parsing entirely! PixelRAG is an open-source visual RAG framework that renders documents as screenshots instead of parsing them into text. Most RAG pipelines start by converting HTML to text. Tables flatten into unstructured rows. Charts disappear. Layout context is gone before the LLM ever sees it. The paper measured this directly: HTML-to-text conversion accounts for 36.6% of retrieval failures on SimpleQA. PixelRAG skips that step entirely. It renders pages as screenshot tiles using Playwright, embeds those tiles with a fine-tuned Qwen3-VL-Embedding model, builds a FAISS index, and passes retrieved images directly to a VLM reader. No text abstraction in between. Benchmarked across six datasets against the strongest text-based baselines: - SimpleQA: 78.8% vs 71.6% (+7.1 points) - NQ-Tables: 48.8% vs 42.5% (+6.3 points) - EVQA: +15.5 points - LiveVQA: +11.3 points One honest caveat from the authors: this requires Qwen3-VL-4B class models or larger to see the benefit. Smaller models trail text retrieval. The authors also recommend using PixelRAG as an enhancement layer alongside existing text systems rather than a full replacement. Ships with a pre-built Wikipedia index covering 8.28M articles across 28.1M screenshot tiles. A Claude Code plugin lets Claude take screenshots of any URL and reason over the visual content directly. Key capabilities: • Renders web pages, PDFs, and images as screenshot tiles via Playwright • Fine-tuned Qwen3-VL-Embedding model for visual retrieval • FAISS index for fast vector search • Pre-built Wikipedia index: 8.28M articles, 28.1M tiles • 3x token cost reduction via image compression • Claude Code plugin for direct URL screenshot and visual reasoning • LoRA fine-tuning support via pixelrag-train 100% open source. I've shared the link in the replies!
显示更多
Sweep roll/ Hand roll. Green River, Utah, 2016. #GetOutside# #LiveRealLife#
0
558
11.8K
446
转发到社区
这周Agent生态有个明显的转向,从写代码到做内容。视频、幻灯片、质量审查,两周内冒出来的工具几乎全是面向产出而非面向开发。 stackblitz/bolt-slides 用任意Agent直接生成交互式演示文稿。Slidev底座加Bolt组件系统,你描述内容它给你一套完整可播放的slide deck,改一版比打开PowerPoint快。 Vincentwei1021/video-shotcraft 用Claude Code或Codex生成电影级产品视频的skill包,内置106张分镜配方卡片和161个运镜预览,底层跑Remotion。从产品截图到成片,一个prompt走完全程。 pyang5166/gbro-collage-broll 把一句话文案变成半调纸拼贴风格动画的skill,Gemini Omni Flash做首尾帧组装。适合不想露脸又想出有质感B-roll素材的内容创作者。 Wunderlandmedia/launchworthy 给AI搭出来的应用做上架前体检的Claude Code skill。测安全、性能、数据库、认证、SEO五个维度,出打分和可直接复制的修复代码。vibe coding出来的app想上线,先过一遍这个。 yc-duan/fastctx Rust写的MCP工具,给Agent提供文件搜索和代码分析能力但极省上下文窗口。代码仓库扔给Agent分析时不用再纠结token爆了的问题。 livetennisapi/livetennisapi-mcp 网球实时比分和胜率预测的MCP服务器。看起来小众,但把任意领域实时数据接进Agent、让Claude或Cursor变成那个领域分析师这条路线,想象空间不小。 MadsGao/frakio-work Electron写的本地多Agent协作工作台,把Codex、Hermes和Arc浏览器缝在一起用。macOS原生应用,所有数据存本地,不用把项目上下文上传到任何云端。 Agent工具生态到了拐点。半年前大家还在讨论Agent能不能写代码,现在问题变成了Agent能不能独立完成一条视频、一套PPT、一个能上线的产品。工具链正在从代码辅助转向全流程输出,这个变化比大部分预想的快。
显示更多
0
15
10
1
转发到社区
Yak attack Cheryl and I bumped into this yak after losing our guide during a ten hour uphill trek above the Tiger’s Nest Monastery near Paro. Immediately before I turned on the camera, she asked, “Do you think it’s dangerous?” Grateful to the yak for retreating when I struck him on the snout with my cell phone. Bhutan, 2013. #GetOutside# #LiveRealLife#
显示更多
0
489
13.1K
488
转发到社区
My mom at Forest Hills 1975. Still light on her feet after 46 years and 100 months pregnant. #GetOutside# #LiveRealLife#
0
565
27.1K
1.1K
转发到社区
BTS WORLD TOUR 'ARIRANG' LIVE VIEWING IN BUSAN Celebrate the special day with BTS. June 13, LIVE VIEWING from BUSAN 🎟️ Tickets-on-sale: May.28 ⏰ 6AM PT | 9AM ET | 2PM BST | 8PM ICT 🔗 More Info: ✅ 국내 예매: 5월 28일 10AM KST 상영관별 순차 오픈 #BTS# #방탄소년단# #BTS_WORLDTOUR_ARIRANG# #BTS_WORLDTOUR_ARIRANG_LIVEVIEWING#
显示更多
0
835
94.3K
37.1K
转发到社区
📢『 #BTS_WORLDTOUR_ARIRANG# IN BUSAN 』 #ライブビューイング# 高陽公演の“熱狂”が蘇る最新予告編を公開🎥 デビュー記念日となる6月13日(土)韓国・釜山アジアド主競技場公演。 特別な日を一緒に体感しましょう✨ さらに、高陽公演を映画館で体験したARMYのコメントも公開💜 詳しくはこちら→ #BTS# #BTS_WORLDTOUR_ARIRANG_BUSAN# #BTS_WORLDTOUR_ARIRANG_LIVEVIEWING#
显示更多
0
48
16.1K
4.1K
转发到社区