Discriminative World Models for Web Agents· 网络代理的世界模型
Recent web agents use world models for test-time action selection by sampling candidate ac…
Recent web agents use world models for test-time action selection by sampling candidate ac…
Harnessing naturally occurring feedback from user interactions offers a promising learning…
Researchers increasingly use artificial intelligence to construct measures of social, orga…
Root cause analysis (RCA) is a critical task in telecom network operations, but diagnosing…
Sign language processing systems have traditionally operated at the sentence level, ignori…
The performance of LLM-based agents is jointly shaped by the base model and the harness us…
Evaluating LLM agents is essential for guiding their development, yet it has grown prohibi…
Low-resource authorship style transfer (LAST) aims to rewrite text into the style of an ar…
Training data attribution (TDA) aims to identify training examples that shape model behavi…
On-premise assistants can give factory workers conversational access to machine documentat…
Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of wor…
Autonomous agents are beginning to carry out machine-learning (ML) research end to end. Th…
Does the door-in-the-face technique work on language models? In humans, a large request th…
Aggregating noisy, conflicting textual hypotheses into a reliable consensus is a fundament…
Generative AI is changing how cultural artifacts are created and circulated, and with it o…
We present CivBench, an open-source benchmark for evaluating language model agents in long…
Large Language Models (LLMs) have recently demonstrated strong capabilities in automated t…
Argumentation frameworks are useful tools for representing and reasoning with information …
With the proliferation of LLM agents, the ability to understand and diagnose failures in a…
Effective in-context learning (ICL) for complex reasoning relies on selecting the right de…
A core obstacle to alignment evaluation is evaluation awareness: capable models can tell w…
The rapid proliferation of large language models (LLMs) and the growing diversity of their…
Model merging provides an efficient paradigm for constructing multi-task large language mo…
Adapting the communication topology of an LLM multi-agent system to each query improves bo…
Deep research agents augment large language models with external tools to answer complex, …
Anti-hallucination for AI agents that read binaries. The model proposes, deterministic too…
This 14 MB Agentic LLM(Cactus Needle 2) can control your phone completely.
Mastering LLM Fine-Tuning in 2026: A Practical Guide from Hugging Face Basics to Productio…
AI Virtual Gym Trainer 2026: OpenCV & MediaPipe Rep Counter with Real-Time Form Feedback
Gemini Spark can edit and curate photo albums, create shared collections, turn photos into…
<img class="rich_pages wxw-img" data-aistatus="1" data-croporisrc="https://mmbiz.qpic.cn/m…
<img class="rich_pages wxw-img" data-aistatus="1" data-croporisrc="https://mmbiz.qpic.cn/s…
过去三年,大模型的快速进步,首先发生在数字世界。文本、图片、代码、视频都可以被转化为数据,模型通过海量预训练学习其中的规律,再完成理解、推理和生成。 但数字世界能够覆盖的任务和场景…
国产卡跑出高品质 AI Token 生产级性能
星尘智能(Astribot) 基座模型团队发布能异步执行的在线强化学习框架 SmoothRL
不训练模型、不调参数
AI音乐公司ACE近日完成近4000万美元新一轮融资,由头部战投、CCV、顺为、Alphaist等机构投资。至此,ACE成为AI音乐赛道融资额最高的华人创业团队之一。 本轮融资将主…
2026年9月3日,云鲸在德国柏林举办2026秋季全球品牌发布会。来自全球多个国家和地区的媒体、合作伙伴与行业嘉宾齐聚现场,共同体验云鲸覆盖扫地机器人、洗地机、吸尘器、除螨仪的家庭…
9月4日,国际数据机构(IDC)发布《中国零售云市场份额,2025》 (以下简称为《报告》)。 腾讯云通过整合PaaS、SaaS及CaaS(咨询即服务)能力,形成覆盖平台、应用及A…
5000支队伍同台做题,写尽行业四年变化
智能不只是模式识别,更是对世界的建模
阿里云千问大模型在办公场景的应用取得显著成效。
While restaurant owners might look to generative AI as a shortcut to sprucing up their men…
今年的WAIC和WRC,具身智能展台的风向变了:不再执着于炫技,转向务实。 去年的画风还是十八般武艺,同台竞技——机器人跳街舞、格斗秀、走猫步等;而今年则是走进真实场景:机器人开始…
吃下90%市场
9月2日,腾讯 WorkBuddy 生态发布会上宣布,与专业音视频硬件品牌HOLLYLAND猛玛达成深度生态合作,推出猛玛LARK A2无线麦克风WorkBuddy联名款。作为首款…
改进GPT Image 2的噪点问题
全球最强C
The high-profile startup's annual revenue run rate stands at over $100 million.
Abliteration.AI is making powerful AI models without guardrails easier to access, arguing …
For its new Muse Spark model, intended for operating coding and other agents, Meta is offe…
OpenAI claims that Astra represents "a new frontier on computer and browser use," and that…
The family-focused AI assistant wants access to the details of your everyday life, but say…
Frontier intelligence is going local. At IFA 2026, NVIDIA, Microsoft and its partners are …
WeatherNext 3 is the latest wave of a sea change in meteorology brought out by deep learni…
9月4日,IFA 2026将于德国柏林展览中心拉开帷幕。作为全球规模最大的消费电子和家用电器博览会之一,IFA吸引了超过1900家参展商,展示从机器人、AI、智能家居到飞行汽车的众…
OpenAI introduces Daybreak for Frontline Defenders. A $1 billion commitment expands access…
<img class="rich_pages wxw-img" data-aistatus="1" data-croporisrc="https://mmbiz.qpic.cn/s…
Using GPT-6 Astra, Playco built three themed game prototypes from one grey box foundation …
Legora used GPT-6 Astra to review 41 documents in minutes, find all four planted errors, a…
GPT-6 Astra is our most capable broadly deployed model and our first to reach the Critical…

YouTube · DeepLearningAI

YouTube · OpenAI

YouTube · OpenAI

YouTube · OpenAI

YouTube · OpenAI

YouTube · OpenAI

YouTube · OpenAI

YouTube · OpenAI

YouTube · OpenAI

YouTube · NVIDIA