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 231

“AI Code Guide”

ニュース記事

How CrossnoKaye grounds physical AI with Amazon Bedrock AgentCore

CrossnoKaye brought physical AI to heavy industry with Amazon Bedrock AgentCore. Its ATLAS platform and AURA agentic system ground AI reasoning in live plant data and run verifiable Python in isolated AgentCore sandboxes, giving plant engineers checkable, math-backed answers instead of model guesses.

Atlas · Specific · Promptニュースを読む ↗
ニュース記事

How skills and agents work in AWS Quick

Repeatable tasks like status updates, release notes, and ticket creation can be encoded in AWS Quick through agents and skills. This post covers how agents, skills, and your data fit together in AWS Quick, how to build and share skills for your team, and how the official catalog and custom agents help you use them.

skills · AI Agents · Write Releaseニュースを読む ↗
ニュース記事

Make a Robot Arm Feel Weightless with NVIDIA Holoscan 5

Picture guiding a robot arm by hand while its motors supply just enough torque to support its weight and keep the robot upright. This simple interaction, a...

英伟达 · Gravity · Perceptionニュースを読む ↗
ニュース記事

n8n@2.48.0

The n8n 2.48.0 release addresses multiple bugs, including fixes for AI builder, compression node, core functionality, editor improvements, and RabbitMQ node issues. New features include enhanced assistant models, Microsoft Work IQ OAuth2 credential support, app bindings UI, migration report enhancements, and improved user experience elements like chat message unification and credential modal restrictions.

UI · n8n · Coreニュースを読む ↗
ニュース記事

n8n@3.2.0

The n8n 3.2.0 release introduces several bug fixes addressing issues in AI Builder, core functionality, editor UI, and node-specific behaviors, including improved handling of JSON, XML, CSV, and YAML responses, enhanced security through expanded IP blocking, and better error reporting. New features include support for Microsoft Work IQ OAuth2 credentials, a new App bindings UI, and updated default Assistant models. The release also reverts some previous changes due to compatibility or stability concerns.

UI · n8n · Coreニュースを読む ↗
ニュース記事

NVIDIA Nemotron 3.5 Super VL is now available in Amazon SageMaker JumpStart

NVIDIA Nemotron 3.5 Super VL, a 120B-parameter multimodal vision-language model, is now available in Amazon SageMaker JumpStart. Deploy the NVFP4 or BF16 variant in a few steps, then run text, image, and video inference for document intelligence, computer-use agents, and multimodal agentic workloads.

英伟达 · Variant · Weightsニュースを読む ↗
ニュース記事

Rethinking Supervision Targets for Multimodal LLM Unlearning: Less Private Information, Reduced Distribution Shift

arXiv:2611.09939v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) can memorize and reproduce sensitive information from their training data, posing significant privacy risks. Their ability to encode knowledge across both textual and visual modalities further complicates the selective removal of such private information. Many existing methods guide model unlearning by training the model toward constructed labels or output distributions, which we refer to as supervision targets. However, these methods often suffer from a trade-off between forgetting effectiveness and model utility. We identify supervision target limitations as a key factor in this trade-off and empirically show that targets containing more private information lead to insufficient forgetting, while larger distribution shifts from the original output distribution are associated with greater utility degradation. Motivated by these findings, we propose FFN-Perturbed Self-Distillation (FPD), which starts from the teacher's original output distribution as a zero-shift reference and selectively perturbs FFN activations associated with private information across textual and visual modalities. By precisely reducing private information from the teacher's original output distribution, FPD constructs supervision targets with less private information and reduced distribution shift. Extensive experiments on S-MLLMUn Bench demonstrate that FPD achieves a better forgetting-utility trade-off than existing methods.

Abstract · Output · Bookmarkニュースを読む ↗
ニュース記事

Show HN: A Terminal UI for Hacker News, and CLI for Agents

hn-cli is a Hacker News client for the terminal. You can use it to browse feeds, stories and comment threads in an elegant full-screen terminal UI. hn-cli also supports search and signed-in actions like voting, favoriting, commenting and submitting. Share feedback! Comments URL: https://news.ycombinator.com/item?id=50432121 Points: 1 # Comments: 0

UI · Specific · Outputニュースを読む ↗
ニュース記事

Show HN: Calculators for token costs and Claude Code API budgets

Article URL: https://modelfold.ai/tools/claude-code-cost Comments URL: https://news.ycombinator.com/item?id=50436457 Points: 2 # Comments: 0

Claude · Claude Code · Outputニュースを読む ↗
ニュース記事

Show HN: Case converter with AP/APA/Chicago/MLA title case

Article URL: https://simplecaseconverter.com/ Comments URL: https://news.ycombinator.com/item?id=50436473 Points: 2 # Comments: 0

Paragraph · Cycle · Outputニュースを読む ↗