AI Intelligence Archive
浏览 AIQB 已保存的 9761 stories AI intelligenceArticles,覆盖Models、Products、Industry、Research、教程与观点方法六大分类。
Indexed articles9761
Categories6
Selected stories2
All articles
Section 130 / 245 页 · 每页 40 stories
ResearchOrdinary
Revisiting Input Time-frequency Representations in Multi-pitch Estimation for Vocal Ensembles
Multi-pitch estimation in vocal ensembles is challenging because singers occupy overlapping pitch ranges and often sing at closely spaced fundamental frequencies, causing their harmonics to overlap in time-frequency representations. Existi…
Source: arXiv
ResearchOrdinary
MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search
Dense-retrieval services must switch among embedding-prefix dimensions and index bit rates as latency, quality, and memory budgets change. Tuning a quantizer separately for each rate gives the best quality, but the retrieval tier then hold…
Source: arXiv
ResearchOrdinary
PoCoFL: POlicy-COmpliant Federated Learning
Federated Learning (FL) is a privacy-oriented learning paradigm that enables collaborative model training while keeping training data local to participating clients. However, it does not guarantee that clients submit policy-compliant contr…
Source: arXiv
ResearchOrdinary
On-Board Anomaly Detection for Efficient Marine Environmental Monitoring
Marine ecosystems are impacted by various threats such as oil spills, algal blooms, and sediment floods, which disrupt habitats, wildlife, and human activities. Advances in satellite imagery and Artificial Intelligence (AI) have enhanced o…
Source: arXiv
ResearchOrdinary
Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models
Many machine learning methods aim to approximate the lower-dimensional manifold on which the data lives. A desirable feature of such methods is that they should capture the epistemic uncertainty of this learned manifold. One model that ach…
Source: arXiv
ResearchOrdinary
When May a Bandit Leave Its Anchor? E-Process-Authorized Thompson Sampling under Non-stationarity
Stationarity rewards memory, but after a change the same history can mislead. We ask when forgetting should be permitted. E-process-authorized Thompson sampling (e-ATS) gives each arm full-history and discounted Beta states. An anytime-val…
Source: arXiv
TutorialsOrdinary
Semantic Versioning Is Not Enough for AI Agent Libraries
A library release can preserve every exported TypeScript type and still change what users...
Source: DEV Community
TutorialsOrdinary
Observabilidade de Trajetórias Agênticas com OpenTelemetry GenAI
Como rastrear trajetórias de agentes de IA com OpenTelemetry GenAI 2.0, detectar loops infinitos em tempo real e aplicar self-healing em produção.
Source: DEV Community
TutorialsOrdinary
How many samples does a false-positive budget need?
Pick a detector, run it over some benign traffic, and choose a threshold. Usually the threshold is an...
Source: DEV Community
TutorialsOrdinary
AI app builders and multi-tenant SaaS: the 30% you still write yourself
Written for: developers who built something real with Lovable, Bolt or v0 and are now being asked to...
Source: DEV Community
TutorialsOrdinary
Building an AI Keyboard for iOS: What They Don't Tell You About Keyboard Extensions
Building an AI Keyboard for iOS: What They Don't Tell You About Keyboard...
Source: DEV Community
TutorialsOrdinary
GGUF VRAM Calculator: Check Before You Download
Model size, quant and context in — weights, KV cache and a per-card verdict out. The GGUF VRAM calculator answers will-it-fit before the download starts.
Source: DEV Community
TutorialsOrdinary
They Learned to Code Before Copilot. They're Not Anti-AI. They're Pro-Evidence.
In July 2025, METR published a study that nobody in a boardroom wanted to read. They took 16...
Source: DEV Community
TutorialsOrdinary
Speculative Decoding for Coding Agents Was Indexing the Wrong Format
Why retrieval speculative decoding falls flat in agent pipelines, and how indexing files in emission format gives a 4.7x throughput boost without a draft model.
Source: DEV Community
TutorialsOrdinary
Don't forget about AI. But build real skills first. Then leverage AI — in that order.
Dear Coder: Open This If You're Feeling AI FOMO Timeless fundamentals beat endless...
Source: DEV Community
TutorialsOrdinary
CodeSmithi: A Textbook Anatomy of Agents: Five Waves of Evolution
Textbook: The Anatomy of an Agent and Five Waves of Evolution Source version of...
Source: DEV Community
PerspectivesOrdinary
https://x.com/i/broadcasts/1mxPaZegOdqKN
https://x.com/i/broadcasts/1mxPaZegOdqKN
Source: X:Replit (@Replit)
ResearchOrdinary
Google 推出 Project Suncatcher
了解More ↓ https://blog.google/innovation-and-ai/models-and-research/google-research/google-project-suncatcher-facts/?utm_source=tw&utm_medium=social&utm_campaign=og
Source: X:Google AI (@GoogleAI)
TutorialsOrdinary
How to Build an AI Research Agent With Citations
Day 2 of 30 Days of Search for AI Agents. I want a research agent to give me something I can check....
Source: DEV Community
TutorialsOrdinary
I Gave 15 AI Models Proof Their Hacking Target Was a Real Company. 73% of the Ones That Noticed Told No One.
This is a submission for the Kaggle Benchmarking Challenge I fed 15 AI models a growing pile of...
Source: DEV Community
TutorialsOrdinary
Afterlight: tiny objects, improbable afterlives, and a human final say
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange. What...
Source: DEV Community
TutorialsOrdinary
Cloud Run instances : héberger un agent IA qui tourne en continu
Les agents IA ne se contentent plus de répondre à une question. Certains travaillent en fond: un...
Source: DEV Community
TutorialsOrdinary
I Built an AI System for 80+ Microservices. Six Months Later, My Whole Team Uses It.
In April I wrote about a system I built on Claude Code that takes an epic to PR-ready code across...
Source: DEV Community · Claude
TutorialsOrdinary
SaS além da vitrine: Service as Software, o que o agente compra e o humano só vê
A gente vai sofrer uma revolução muito rápida. Os agentes pessoais já estão no caminho: Dots, Grok...
Source: DEV Community · Grok
TutorialsOrdinary
Road to State Machines IV - But How Do We Let Data Influence Transitions Without Turning Every Value into Another State?
Our lifecycle now has one explicit transition table. For a valid order, it tells us: The operations...
Source: DEV Community
TutorialsOrdinary
Agent health from a 60-second heartbeat: derived, never stored
In my ticket tracker an agent's status is never stored as alive or dead. The orchestrator beats once a minute, and every screen works out the dot from
Source: DEV Community
TutorialsOrdinary
I Built a Claude Code Skill That Makes AI Agents Prove Their Answers
AI coding agents are getting very good at navigating repositories. Ask an agent: "Where is the API...
Source: DEV Community · Claude
TutorialsOrdinary
A Coding Agent Added Jetpack Compose Support to My Android Renderer MCP. I Wouldn't Have Started This Task Myself.
Android UI Renderer MCP is a local MCP server that lets a coding agent render Android UI without an...
Source: DEV Community
TutorialsOrdinary
How I Built a Post-Mortem Loop So My AI Coding Agent Stops Repeating Mistakes
TL;DR My fully autonomous implementation system kept making the same handful of mistakes...
Source: DEV Community
TutorialsOrdinary
LensLink: An AI Camera Compatibility Agent Powered by Structured Sanity Content
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real...
Source: DEV Community
TutorialsOrdinary
Caveman: Make Your AI Coding Agent Talk Less (and Save Tokens)
If you use an AI coding agent every day, you have probably noticed how much of its output is padding....
Source: DEV Community
TutorialsOrdinary
I Said Isolation Was Structural. Then Tenancy Shipped and Proved Me Right the Hard Way
In the last piece of my v0.1.0 series I wrote a sentence I was proud of and not yet entitled to:...
Source: DEV Community
TutorialsOrdinary
Agents that forget where they are will repeat work forever — checkpointing is the save-point pattern you need — Checkpointing and Resume
I watched a research pipeline die at step nine of ten. Forty-three minutes of work, sixty sources...
Source: DEV Community
TutorialsOrdinary
Hacktoberfest 2026 Stopped Counting PRs. How I'd Spend the Month Instead
Hacktoberfest 2026 has no pull request quota, and I think that frees you to do the kind of open...
Source: DEV Community
TutorialsOrdinary
I Think We Confuse Clean Code With Good Code
I've seen beautifully organized code that was difficult to understand. I've also seen ugly-looking...
Source: DEV Community
ResearchOrdinary
S$^{2}$-PINN: Stochastic Separable Physics-Informed Neural Networks
Uncertainty quantification (UQ) for random partial differential equations (PDEs) is ubiquitous in computational science and engineering. However, classical spectral solvers for this class of problems face the curse of dimensionality, and e…
Source: arXiv
ResearchOrdinary
JOVE: Joint Execution and Verification for Resource-Aware LLM Task Graphs
Complex reasoning queries can be decomposed into directed acyclic task graphs and distributed across heterogeneous LLMs, reducing latency through parallelism and enabling smaller models to solve complex tasks. In practice, however, the sui…
Source: arXiv
TutorialsOrdinary
Export ChatGPT, Claude, Gemini, Grok, DeepSeek, Kimi, and Qwen chats to Markdown with Convolvger 0.6.0
If you have ever tried to export a ChatGPT conversation to Markdown, or save a Claude chat as a .md...
Source: DEV Community · ChatGPT / DeepSeek / Qwen
ResearchOrdinary
Wrong Organ, Right Physics: Transferring Echocardiography Pretraining to Lung Ultrasound for Tuberculosis Screening
Lung ultrasound (LUS) is attractive for tuberculosis (TB) screening at primary-care level, but labelled cohorts are small. Echocardiography carries no such constraint, while sharing the same underlying ultrasound imaging physics, signal pr…
Source: arXiv
ResearchOrdinary
Architecture-Dependent Fusion Pathways in MLLMs
Multimodal Large Language Models (MLLMs) achieve strong performance across vision-language tasks, yet the internal mechanisms by which visual and textual information are fused across layers remain insufficiently understood. We investigate …
Source: arXiv