←搜索结果

按匹配度 · 共 87 条结果 清除搜索

星期一

  1. MiniMax Blog

    MiniMax 发布 M3:前沿编码、1M 上下文与原生多模态合一

    MiniMax 正式发布 M3,采用自研 MSA 稀疏注意力架构,支持最高 1M token 上下文,并原生支持图像与视频输入、可操作桌面电脑。官方称 M3 是目前首个同时具备这三项能力的开源权重模型,在 SWE-Bench Pro 得分 59.0%、Terminal-Bench 2.1 得分 66.0%、MCP Atlas 得分 74.2%。M3 已通过 MiniMax Code、Token Plan 和 API 开放使用,官方表示将在未来 10 天内发布技术报告并开源模型权重。

    model weights. Today, models are being updated at such a fast pace that it is easy to forget this is still a matter of steady, incremental progress. It follows its own objective laws, and it rewards teams that move forward solidly in accordance with those laws. Just as we believed at the very beginning of our founding, we will do our utmost to continuously improve the intelligence of our models and make them available to more users. Thank you for your trust, suggestions, and criticism. Intellig

    匹配字段正文

星期五

  1. Claude 应用发布说明精选

    Anthropic 发布 Claude Opus 4.8

    Anthropic 发布 Claude Opus 4.8,在编码、智能体、推理等基准上较 Opus 4.7 有所提升,价格不变。同时推出 claude.ai 上的努力程度控制、Claude Code 的动态工作流功能,以及快模式降价三倍。

    ts work and less likely to make unsupported claims. This is borne out in our evaluations, which show that Opus 4.8 is around four times less likely than its predecessor to allow flaws in code it has written to pass unremarked. As always, we ran a detailed alignment assessment on the model before release. In terms of positive traits, our Alignment team concluded that Opus 4.8 “reaches new highs on our measures of prosocial traits like supporting user autonomy and acting in the user’s best interes

    匹配字段正文

星期二

  1. Google DeepMind精选

    Google DeepMind 推出 Gemini Omni

    Google DeepMind 推出 Gemini Omni,其首款模型 Gemini Omni Flash 可接收图像、音频、视频和文本输入,生成高质量视频,并支持通过多轮自然语言对话编辑。该模型正向 Gemini app、Google Flow 和 YouTube Shorts 推出,未来数周将通过 API 面向开发者和企业客户开放;初期音频输入仅支持语音参考,生成视频均含 SynthID 数字水印。

    The image shows a colorful abstract design with the Google I/O 2026 logo.

    namics, allowing you to create more realistic scenes. Prompt: A marble rolling fast on a chain reaction style track, continuous smooth shot. Blend knowledge and creativity. Omni draws on Gemini's knowledge to connect language, imagery and meaning in ways that go far beyond pattern matching. Complex ideas made visual. Omni can create compelling explainers from short prompts, generating visuals that break down more complex ideas. Prompt: claymation explainer of protein folding, everything is made

    匹配字段正文

星期四

  1. Qwen Blog精选

    阿里千问发布 Qwen3.6-Plus,主打真实世界智能体能力

    阿里千问发布 Qwen3.6-Plus,通过阿里云百炼 API 提供,默认 1M 上下文窗口,重点提升智能体编码与多模态感知推理能力。官方基准显示其在 SWE-bench Verified 得 78.8、Terminal-Bench 2.0 得 61.6、QwenClawBench 得 57.2,均高于 Qwen3.5-397B-A17B。API 新增 preserve_thinking 参数用于保留多轮思考内容,默认关闭,可接入 Claude Code、Qwen Code、Cline、OpenCode 等编码工具。

    onal signage is presented in Appendix 3. Page 26. EAZA Best Practice Guidelines. Asian giant forest tortoise (Manouria emys). Date: Dec 4, 2025 [64] https://s3-us-gov-west-1.amazonaws.com/cg-654ebf73-8576-4082-ba73-dd1f1a7fe8dc/uploads/USTDA-Indo-Pacific-Resource-Guide-EDIT 0.pdf Title: [PDF] USTDA Indo Pacific Resources Guide EDIT 0.pdf - Amazon S3 Snippet: Sabah Oil and Gas Development Corporation Sdn Bhd (SOGDC) is a wholly-owned company of the state of Sabah designated as the vehicle to own,

    匹配字段正文

星期四

  1. Sarvam AI Blog

    Sarvam AI 发布 3B 状态空间视觉语言模型 Sarvam Vision

    Sarvam AI 发布 Sarvam Vision,这是一个 3B 参数的状态空间视觉语言模型,支持图像描述、场景文字识别、图表解读和复杂表格解析等任务。该模型在 olmOCR-Bench、OmniDocBench V1.5 以及自建的 Sarvam Indic OCR Bench(含 22 种印度官方语言、20267 个样本)上报告了性能,并称在印度语言上准确率优于通用模型。官方同时宣布 2026 年 2 月整月免费开放 Document Intelligence API 与 Vision 体验,可通过 dashboard.sarvam.ai 使用。

    uilding. The shop appears to be a local bookstore or library. A low resource Indic Language output The image depicts a busy street scene in an urban area. There are two auto-rickshaws, one black and one green, driving on the road. Several people are walking on the street, and there are various shops and buildings on either side of the street. The sky is blue with some clouds. For the above image, the model was prompted to describe the scene in Santhali (a low-resource Indian language). Instructi

    匹配字段正文

星期三

  1. Mistral AI精选

    Mistral AI 推出 Mistral 3

    Mistral AI 推出 Mistral 3 模型家族,包括 3B、8B 和 14B 的 Ministral 3,以及采用稀疏 MoE 架构、含 41B 激活参数和 675B 总参数的 Mistral Large 3,均以 Apache 2.0 许可证发布。Ministral 3 提供 base、instruct 和 reasoning 版本,Mistral Large 3 提供 base 与 instruct 版本并将推出 reasoning 版本;该系列现已登陆 Mistral AI Studio、Amazon Bedrock、Azure Foundry、Hugging Face 等平台。

    Chart Base Models (1)

    n Bedrock , Azure Foundry, Hugging Face ( Large 3 & Ministral ), Modal , IBM WatsonX, OpenRouter, Fireworks, Unsloth AI,and Together AI. In addition, coming soon on NVIDIA NIM and AWS SageMaker. For organizations seeking tailored AI solutions, Mistral AI offers custom model training services to fine-tune or fully adapt our models to your specific needs. Whether optimizing for domain-specific tasks, enhancing performance on proprietary datasets, or deploying models in unique environments, our tea

    匹配字段正文

星期六

  1. Sarvam AI Blog

    Sarvam AI 发布 Sarvam-Translate,支持 22 种印度语言

    Sarvam AI 与 AI4Bharat 合作发布开源权重翻译模型 Sarvam-Translate,基于 Gemma3-4B-IT 微调,支持 22 种印度语言的段落级翻译,并为 15 种语言提供结构化内容翻译。模型可保留 HTML、LaTeX、化学公式、代码和 SRT 字幕等格式,仅翻译可读文本。语言专家人工评测显示其表现优于 Gemma3-27B-IT、Llama4 Scout 和 Llama-3.1-405B-FP8 等更大模型,模型已在 Hugging Face 开源并提供 API。

    Sarvam Translate

    rmissible arrogation of essential legislative functions by the executive, a proposition anathema to the constitutional scheme of separation of powers, as expounded in In Re Delhi Laws Act, 1912 (AIR 1951 SC 332) and reiterated consistently thereafter, including in Hamdard Dawakhana (Wakf) Lal Kuan, Delhi v. Union of India (AIR 1960 SC 554); Furthermore, it is strenuously canvassed that the Impugned Rules are vitiated by manifest arbitrariness, thereby infracting Article 14 of the Constitution. T

    匹配字段正文