rui 的 blog

菜单

Administrator
发布于 2026-03-18 / 3 阅读
0
0

AI 每日资讯 - 2026-03-18

发布日期：2026-03-18

收录条目：20

1. Unsloth AI Releases Unsloth Studio: A Local No-Code Interface For High-Performance LLM Fine-Tuning With 70% Less VRAM Usage

摘要：The transition from a raw dataset to a fine-tuned Large Language Model (LLM) traditionally involves significant infrastructure overhead, including CUDA environment management and high VRAM requirements. Unsloth AI, known

2. Nvidia’s DLSS 5 is like motion smoothing for video games, but worse

摘要：Yesterday Nvidia revealed its latest upscaling tech, called DLSS 5, which it described as "the company's most significant breakthrough in computer graphics since the debut of real-time ray tracing in 2018." Sounds good,

3. Now everyone in the US is getting Google’s personalized Gemini AI

摘要：Google announced on Tuesday that all users in the US will now have access to its Personal Intelligence feature, which lets you connect various Google apps to provide context for Gemini's responses and suggestions. Access

4. Bringing the power of Personal Intelligence to more people

摘要：We're expanding Personal Intelligence across AI Mode in Search, the Gemini app and Gemini in Chrome.

5. Our latest investment in open source security for the AI era

摘要：Google is making new investments, building new tools and developing code security to improve open source security.

6. AWS AI League: Atos fine-tunes approach to AI education

摘要：In this post, we’ll explore how Atos used the AWS AI League to help accelerate AI education across 400+ participants, highlight the tangible benefits of gamified, experiential learning, and share actionable insights you

7. Microsoft appoints a new Copilot boss after AI leadership shake-up

摘要：Microsoft is doing another executive shuffle today to reorganize how it engineers its Copilot assistant. Different teams have been working on the consumer and commercial sides of Copilot for years, but Microsoft is about

8. The future of code is exciting and terrifying

摘要：Suddenly it seems like everyone's a coder. Or, at the very least, like they play one in the Claude Code app. But even for the seasoned pros, the act of software development is changing fast - many people are writing less

9. Introducing GPT-5.4 mini and nano

摘要：GPT-5.4 mini and nano are smaller, faster versions of GPT-5.4 optimized for coding, tool use, multimodal reasoning, and high-volume API and sub-agent workloads.

10. Google AI Releases WAXAL: A Multilingual African Speech Dataset for Training Automatic Speech Recognition and Text-to-Speech Models

摘要：Speech technology still has a data distribution problem. Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) systems have improved rapidly for high-resource languages, but many African languages remain poorly rep

11. How to Build High-Performance GPU-Accelerated Simulations and Differentiable Physics Workflows Using NVIDIA Warp Kernels

摘要：In this tutorial, we explore how to use NVIDIA Warp to build high-performance GPU and CPU simulations directly from Python. We begin by setting up a Colab-compatible environment and initializing Warp so that our kernels

12. Human Attribution of Causality to AI Across Agency, Misuse, and Misalignment

摘要：arXiv:2603.13236v1 Announce Type: new Abstract: AI-related incidents are becoming increasingly frequent and severe, ranging from safety failures to misuse by malicious actors. In such complex situations, identifying whic

13. A Dual-Path Generative Framework for Zero-Day Fraud Detection in Banking Systems

摘要：arXiv:2603.13237v1 Announce Type: new Abstract: High-frequency banking environments face a critical trade-off between low-latency fraud detection and the regulatory explainability demanded by GDPR. Traditional rule-based

14. Benchmarking Zero-Shot Reasoning Approaches for Error Detection in Solidity Smart Contracts

摘要：arXiv:2603.13239v1 Announce Type: new Abstract: Smart contracts play a central role in blockchain systems by encoding financial and operational logic. Still, their susceptibility to subtle security flaws poses significan

15. Think First, Diffuse Fast: Improving Diffusion Language Model Reasoning via Autoregressive Plan Conditioning

摘要：arXiv:2603.13243v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) generate text via iterative denoising but consistently underperform on multi-step reasoning. We hypothesize this gap stems from a co

16. Automating Document Intelligence in Statutory City Planning

摘要：arXiv:2603.13245v1 Announce Type: new Abstract: UK planning authorities face a legislative conflict between the Planning Act, which mandates public access to application documents, and the Data Protection Act, which requ

17. Multi-Axis Trust Modeling for Interpretable Account Hijacking Detection

摘要：arXiv:2603.13246v1 Announce Type: new Abstract: This paper proposes a Hadith-inspired multi-axis trust modeling framework, motivated by a structurally analogous problem in classical Hadith scholarship: assessing the trus

18. ILION: Deterministic Pre-Execution Safety Gates for Agentic AI Systems

摘要：arXiv:2603.13247v1 Announce Type: new Abstract: The proliferation of autonomous AI agents capable of executing real-world actions - filesystem operations, API calls, database modifications, financial transactions - intro

19. ManiBench: A Benchmark for Testing Visual-Logic Drift and Syntactic Hallucinations in Manim Code Generation

摘要：arXiv:2603.13251v1 Announce Type: new Abstract: Traditional benchmarks like HumanEval and MBPP test logic and syntax effectively, but fail when code must produce dynamic, pedagogical visuals. We introduce ManiBench, a sp

20. When Alpha Breaks: Two-Level Uncertainty for Safe Deployment of Cross-Sectional Stock Rankers

摘要：arXiv:2603.13252v1 Announce Type: new Abstract: Cross-sectional ranking models are often deployed as if point predictions were sufficient: the model outputs scores and the portfolio follows the induced ordering. Under no

NoSuchUpload 复盘：为...

评论