时间线归档 - AI Stack

CHRONOLOGICAL LEDGER

按时间浏览

PAGE 32

2026 年

50 篇

三月

50 ENTRIES

Build an AI-Powered A/B testing engine using Amazon Bedrock | Amazon Web Services

BLOGS_PODCASTS 博客与播客 MCP

阅读文章

Beyond Muon: MUD (MomentUm Decorrelation) for Faster Transformer Training

ARXIV ArXiv

阅读文章

AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse

ARXIV ArXiv AI Agent

阅读文章

A better method for identifying overconfident large language models

BLOGS_PODCASTS 博客与播客大语言模型

阅读文章

2% of ICML papers desk rejected because the authors used LLM in their reviews

HACKER_NEWS Hacker News 大语言模型

阅读文章

SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models

ARXIV ArXiv 大语言模型

阅读文章

Online Experiential Learning for Language Models

ARXIV ArXiv 大语言模型

阅读文章

ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100K

ARXIV ArXiv

阅读文章

Long-Horizon Traffic Forecasting via Incident-Aware Conformal Spatio-Temporal Transformers

ARXIV ArXiv

阅读文章

Launch an autonomous AI agent with sandboxed execution in 2 lines of code

HACKER_NEWS Hacker News AI Agent

阅读文章

Efficient Reasoning on the Edge

ARXIV ArXiv 大语言模型

阅读文章

Demystifing Video Reasoning

ARXIV ArXiv

阅读文章

Chronos: Temporal-Aware Conversational Agents with Structured Event Retrieval for Long-Term Memory

ARXIV ArXiv AI Agent

阅读文章

Why AI systems don't learn – On autonomous learning from cognitive science

HACKER_NEWS Hacker News

阅读文章

Mistral AI Releases Forge

HACKER_NEWS Hacker News

阅读文章

Unsloth Studio

HACKER_NEWS Hacker News

阅读文章

Ranking Engineer Agent (REA): The Autonomous AI Agent Accelerating Meta’s Ads Ranking Innovation

BLOGS_PODCASTS 博客与播客 AI Agent

阅读文章

MIT-IBM Watson AI Lab seed to signal: Amplifying early-career faculty impact

BLOGS_PODCASTS 博客与播客 AI Agent

阅读文章

Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

HACKER_NEWS Hacker News

阅读文章

Toward automated verification of unreviewed AI-generated code

HACKER_NEWS Hacker News

阅读文章

SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval

ARXIV ArXiv 大语言模型

阅读文章

Robust and Computationally Efficient Linear Contextual Bandits under Adversarial Corruption and Heavy-Tailed Noise

ARXIV ArXiv

阅读文章

OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data

ARXIV ArXiv AI Agent

阅读文章

Mixture-of-Depths Attention

ARXIV ArXiv 大语言模型

阅读文章

Mechanistic Origin of Moral Indifference in Language Models

ARXIV ArXiv 大语言模型

阅读文章

HorizonMath: Measuring AI Progress Toward Mathematical Discovery with Automatic Verification

ARXIV ArXiv 大语言模型

阅读文章

From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation

ARXIV ArXiv

阅读文章

Do Metrics for Counterfactual Explanations Align with User Perception?

ARXIV ArXiv

阅读文章

Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning

ARXIV ArXiv 大语言模型

阅读文章

AWS AI League: Atos fine-tunes approach to AI education | Amazon Web Services

BLOGS_PODCASTS 博客与播客大语言模型

阅读文章

AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer

ARXIV ArXiv

阅读文章

告别 AI 名词焦虑：一文读懂从 LLM 到 Agent Skill的演进

JUEJIN 掘金 MCP

阅读文章

Show HN: March Madness Bracket Challenge for AI Agents Only

HACKER_NEWS Hacker News AI Agent

阅读文章

Show HN: Antfly: Distributed, Multimodal Search and Memory and Graphs in Go

HACKER_NEWS Hacker News

阅读文章

Introducing GPT-5.4 mini and nano

BLOGS_PODCASTS 博客与播客命令行工具

阅读文章

AI辅助开发最佳实践：2026年新方法

JUEJIN 掘金 MCP

阅读文章

AI 对话应用之 JS 的流式接口数据处理

JUEJIN 掘金 Java

阅读文章

零基础学 Agent ：拆解一个 Agent 的「零件清单」——8 个模块逐一讲透第 2 期

JUEJIN 掘金 RAG

阅读文章

编码 Agent 如何重塑工程、产品与设计

JUEJIN 掘金 AI Agent

阅读文章

A2UI：让 AI Agent "说出"用户界面的开放协议

JUEJIN 掘金 MCP

阅读文章

清华团队开源！1 键生成多 Agent 智能体 AI 课堂。

JUEJIN 掘金 AI Agent

阅读文章

从MVP到千万级并发 AI在前后端开发中的差异化落地指南

JUEJIN 掘金 RAG

阅读文章

OPC时代，AI底座先行——FlagOS携Qwen3-8B镜像正式登陆阿里云

JUEJIN 掘金 AI Agent

阅读文章

MiniMax M2.5：从黑马到全球顶流的"前世今生"与趣闻

JUEJIN 掘金 AI Agent

阅读文章

文件即真理：深度解析 OpenClaw 的 Markdown 记忆系统

JUEJIN 掘金 AI Agent

阅读文章

Spiking Layer-Adaptive Magnitude-based Pruning

ARXIV ArXiv

阅读文章

SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated Learning

ARXIV ArXiv

阅读文章

RS-WorldModel: a Unified Model for Remote Sensing Understanding and Future Sense Forecasting

ARXIV ArXiv

阅读文章

LLM as Graph Kernel: Rethinking Message Passing on Text-Rich Graphs

ARXIV ArXiv 大语言模型

阅读文章

Lightweight User-Personalization Method for Closed Split Computing

ARXIV ArXiv

阅读文章