本文へ移動
AI NEWS JOURNAL
AI NEWS / SEARCH

ニュースとサイト内検索

ニュース、ツール、モデル、ガイド、特集、ワークフロー、プロンプトを関連付けて検索。

ニュース記事 230

“AI Code Guide”

ニュース記事

Show HN: BrowserForge – AI agents use your real browser, you approve the clicks

Article URL: https://github.com/zoghlamimostafa/BrowserForge-MCP Comments URL: https://news.ycombinator.com/item?id=50373055 Points: 1 # Comments: 0

MCP · AI Agents · docsニュースを読む ↗
ニュース記事

Show HN: Edgepad – Turn an Android phone into a trackpad for your laptop

Article URL: https://github.com/akshit-bansal11/edgepad Comments URL: https://news.ycombinator.com/item?id=50374433 Points: 1 # Comments: 1

Reach · Pinch · Arrowニュースを読む ↗
ニュース記事

Show HN: Mdview Desktop – light, fast and feature-rich Markdown viewer (Windows)

Article URL: https://mdview.io/desktop Comments URL: https://news.ycombinator.com/item?id=50371428 Points: 1 # Comments: 0

Read It · Natively · Sequenceニュースを読む ↗
ニュース記事

Show HN: Sunlith, an Android calendar you can control through MCP

Article URL: https://github.com/SunSinD/Sunlith Comments URL: https://news.ycombinator.com/item?id=50375585 Points: 1 # Comments: 0

MCP · Codex · Claudeニュースを読む ↗
ニュース記事

Show HN: Telegram AI assistant with projects, images and background jobs

Article URL: https://github.com/watscho/chat-gpt-telegram-bot Comments URL: https://news.ycombinator.com/item?id=50377737 Points: 1 # Comments: 0

Telegram · AI Assistant · Backgroundニュースを読む ↗
ニュース記事

Show HN: ZeBridge – PostgreSQL replicas on devices, synchronized over NATS

Article URL: https://github.com/ndrean/ZeBridge Comments URL: https://news.ycombinator.com/item?id=50376801 Points: 1 # Comments: 0

Compose · Writer · Rowsニュースを読む ↗
ニュース記事

A thousand fewer paths to root

OpenAI built an autonomous pipeline that found, validated, and generated patches for 948 local privilege-escalation vulnerabilities in the Linux kernel.

OpenAI · Relevant · Outputニュースを読む ↗
ニュース記事

b12099

The update introduces initial support for the LIGHTNING_INDEXER operation in the Hexagon backend, including optimizations for HMX prefill, q4_0 and f32 K support, pipelined HMX paths, improved DMA pipeline with canonical double buffering, and enhanced kernel parameter alignment. It also adds options to force HMX/HVX execution paths and supports dimension collapse.

Hex · Lid · LLaMAニュースを読む ↗
ニュース記事

From Visual Matching to Textual Conditioning: Cross-Domain Few-Shot Segmentation via Reference Inversion

arXiv:2611.04084v1 Announce Type: new Abstract: Cross-Domain Few-Shot Segmentation (CD-FSS) aims to segment objects from unseen domains using only a few annotated references. Recent Segment Anything Model (SAM)-based methods have advanced CD-FSS, yet their reference-target visual matching is highly sensitive to target appearance variations. SAM3 introduces text-conditioned segmentation, enabling natural-language descriptions to guide segmentation across target images, but directly using the category name as the condition still yields unstable performance under severe domain shifts. We propose Reference Inversion for SAM3 (RI-SAM3) that leverages SAM3's large-scale vision-language pre-training to learn suitable textual tokens for each target category. RI-SAM3 comprises three core designs: (i) Bi-level Reference Inversion that learns complementary tokens before and after the frozen text encoder: the former remain anchored in SAM3's text space while the latter represent the category more flexibly; (ii) Layer-adaptive Textual Conditioning combines these tokens differently as object queries evolve across decoder layers; and (iii) Presence-aware Confidence Supervision that jointly supervises query confidence and target presence for reliable predictions. With SAM3 frozen, RI-SAM3 optimizes around 12K parameters only per category and it efficiently segments each target in a single forward pass with reusable textual conditioning without per-sample reference-target visual matching. Extensive experiments over multiple widely adopted benchmarks show that RI-SAM3 achieves superior performance consistently in CD-FSS tasks, together with strong robustness, efficiency, and generalization.

Abstract · SAM · Segment Anything Model (SAM)ニュースを読む ↗
ニュース記事

Introducing Images 2.6

Images 2.6 brings faster image generation, GIF creation, more precise editing, and new API controls across ChatGPT, Codex, and the API.

ChatGPT · Codex · Detailニュースを読む ↗