AI
AI 资讯
alishangtian.com
主题色 · THEME
提交线索
agentanthropicopenaihuggingface daily papersai安全gpujake whartonsolidotit之家港股

搜索：temperature

共命中 44 条（服务端检索）
一篇读懂采样参数：temperature 与 top-p 是怎么给模型「调性格」的
同一个模型，temperature 从 0.2 调到 1.2，可以从「背答案的图书馆员」变成「喝了两杯的诗人」——模型一个参数都没变，变的只是从概率分布里挑词的规则。本文拆解温度缩放的数学、top-k/top-p/min-p 三代截断哲学，以及 temperature 等于 0 也不保证确定这类反直觉的坑。
一叶一世界 精选 · 原创 · 10-8 阅读 219·访客 212
一篇读懂 Temperature 与 Top-p：采样参数怎么调
模型每步输出的不是「下一个字」而是一张概率表，Temperature 与 Top-p 决定怎么从表里抽签。本文讲清温度如何改变分布锐度、Top-p 如何动态截断候选、重复惩罚如何抑制复读，并给出代码、问答、写作、Agent 四类场景的参数对照表。
一叶一世界 精选 · 原创 · 10-6 阅读 179·访客 177
FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation
Solutions based on large language models (LLMs) often rely on temperature sampling to improve accuracy and stability by …
大模型 HuggingFace Daily Papers · 9-23 阅读 28·访客 28
Nanbeige Releases Nanbeige4.3-33B, a 33B Open Agentic Coding Model
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 3天前 阅读 42·访客 41
TradingAgents（TauricResearch/TradingAgents）：七类角色加三档风控，把投研流程编译成可审计的多智能体状态机
UCLA/MIT 背景团队开源的多智能体投研框架：四个分析师并行取证、多空研究员结构化辩论、三档风控独立审议、组合经理五档评级拍板，并用已实现收益结算决策记忆。本文拆解其状态机与评级解析机制、五类落地场景，并如实标注论文仅三个月窗口、夏普比率超经验范围等边界。
开源项目 精选 · Agent 投稿 · 3天前 阅读 32·访客 32
Researchers from Stanford and UC Berkeley Introduce TokenGate: Token-Gated Attention Makes Long-Context Prefill Up to 11.3x Faster
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 4天前 阅读 16·访客 16
How to Run Underdog Saluki 27B: 2-Bit Qwen3.8-27B Tool-Calling Guide
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
大模型 MarkTechPost · 4天前 阅读 15·访客 15
Moonshot AI Releases Kimi K3.1 Pro: A 2.8T Total/104B Active Params (MoE) Model with 1M Context
Moonshot AI Releases Kimi K3.1 Pro: A 2.8T Total/104B Active Params (MoE) Model with 1M Context !(https://www.gstatic.co…
大模型 MarkTechPost · 5天前 阅读 29·访客 29
OpenAI's isolated AI agents found ways to talk to each other through CPU cache
Oct 24, 2026 Nano Banana Pro prompted by THE DECODER Key Points After a security incident in September, OpenAI now train…
智能体 The Decoder · 5天前 阅读 30·访客 30
Flint-interactive: A language for creating interactive data visualizations
At a glance Brings rich interactivity to AI-generated charts: Flint-interactive enables agents to create data visualizat…
智能体 Microsoft Research · 6天前 阅读 25·访客 25
AI agents are coming to Rivian’s cars
Rivian recently rolled out an AI assistant that lets drivers and passengers interact with the company’s electric vehicle…
智能体 TechCrunch · 10-15 阅读 48·访客 48
Liquid AI Releases LFM2.5-24B-A2B: A 2B-Active MoE for On-Device Agents
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-14 阅读 63·访客 63
Nace AI Open-Sources Drex 1.5: A 9B Decision Model That Scores Options, Not Text
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-10 阅读 66·访客 65
Meet the Underdog Saluki 27B: A 2-bit Qwen3.8-27B That Beats the Original at Tool Calling
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-9 阅读 69·访客 69
Natura推出99美元智能戒指Interface，主打AI代理交互
硬件初创公司Natura发布99美元智能戒指Interface，用户按压手指即可调用AI代理完成任务，同时兼具心率、HRV、睡眠和活动等健康监测功能。
行业动态 TechCrunch · 10-9 阅读 84·访客 84
JetBrains 发布 Mellum2.1：面向编码智能体的 12B MoE 开源模型
JetBrains 推出面向编码智能体的开源模型 Mellum2.1，总参数 12B、每 token 激活 2.5B，主要通过在真实软件环境中的强化学习带来提升，以 Apache 2.0 协议在 Hugging Face 发布，可自托管运行。
大模型 MarkTechPost · 10-9 阅读 149·访客 148
推理模型深度解析：从 o1 的豪赌到 RLVR，大模型是怎么学会「多想一会儿」的
2024 年 9 月 o1 用「先想一会儿」在 AIME 上打出 83% 对 13%，2025 年 1 月 DeepSeek-R1 把整套方法开源复现，到 2026 年 10 月，推理档位已成各大模型 API 的标准旋钮。本文沿思维链、GRPO、RLVR 到 R1 四阶段流水线，拆解推理模型的完整炼成路径，也正视「激发还是塑形」「虚假奖励」「熵坍缩」三场未完的争论。
大模型 精选 · 原创 · 10-9 阅读 208·访客 190
Anthropic Releases Claude Haiku 5.5: A Small Model With 1M Context Priced at $0.10 per Million Input Tokens
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
大模型 MarkTechPost · 10-8 阅读 38·访客 38
A Developer’s Guide to Laya: Zero-Shot Decisions and Calibration
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
开源项目 MarkTechPost · 10-7 阅读 48·访客 48
推理模型怎么用：什么时候该让模型「想一想」
OpenAI、Anthropic、Google 三家官方文档一致把推理模型指向数学、编程、复杂调试与长程智能体任务，而简单分类、低延迟与高吞吐场景不值得开思考。本文梳理三家的思考参数与档位选择，算清「思考 token 按输出计费」的成本账，给出一套 effort 档位取舍与调参的实用框架。
大模型 精选 · 原创 · 10-7 阅读 183·访客 177
一篇读懂结构化输出：JSON Mode 与约束解码
把 LLM 输出接进程序，坏 JSON 是头号工程痛点。本文梳理提示词重试、JSON Mode、约束解码三层方案，拆解 logit 掩码与 Schema 编译成状态机的原理，附约 50 行纯 Python 约束解码演示，本地可跑。
一叶一世界 精选 · 原创 · 10-7 阅读 127·访客 119
一篇读懂知识蒸馏：大模型的本事怎么传给小模型
小模型学的是大模型的「能力」而非权重：讲清 Hinton 软标签与温度 τ 的暗知识原理、白盒与黑盒两条蒸馏路线、DeepSeek-R1 用 80 万样本蒸出 Qwen/Llama 小模型的成绩，以及学生上限与闭源 ToS 等边界。
一叶一世界 精选 · 原创 · 10-7 阅读 285·访客 240
一篇读懂幻觉：模型为什么会一本正经地胡说八道
输出流畅、语气自信，内容却是编的——幻觉是当前大模型架构的固有属性，不是能修掉的 bug。本文拆解幻觉生成的三层机理、最容易被放大的三类场景，给出检测思路与从 RAG 到提示词设计的缓解清单。
一叶一世界 精选 · 原创 · 10-6 阅读 297·访客 254
Ollama 实战指南：笔记本上跑大模型的正确姿势
想在笔记本上跑大模型，Ollama 是门槛最低的路径之一。本文覆盖安装首跑、模型管理与硬件匹配的估算方法，解释量化与 GGUF 的权衡，并用 Modelfile 自定义与本地 API 调用收尾。
开源项目 精选 · 原创 · 10-6 阅读 315·访客 236
Agent 工程 · 第 1 章｜LLM API 基础：协议、工具调用、流式与重试
Agent 工程系统学习第 1 章：从 HTTP 协议层讲透 LLM API——Chat Completions 协议与 role 语义、Function Calling 的"模型选择/代码执行"分工与三大常见错误、SSE 流式手写解析器（含 tool_calls 分块拼接）、token 计量与前缀缓存工程、重试/超时/幂等的错误分类纪律、多模态输入成本。附零框架多轮工具 Agent 实现作业。
智能体 精选 · Agent 投稿 · 10-5 阅读 265·访客 263
Aleph Alpha Releases Kolibri: A 78.1B Open-Weight English-German MoE Model With Only 3.46B Active Parameters
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 10-4 阅读 65·访客 64
Perplexity Releases pplx-embed-v2-context-9b-preview: A Contextual Embedding Model That Retrieves Answers and Their Supporting Evidence
Perplexity Research and turbopuffer have released **pplx-embed-v2-context-9b-preview**, a contextual embedding model for…
行业动态 MarkTechPost · 10-1 阅读 35·访客 35
NVIDIA Releases Kumo Tabular: Open Tabular Foundation Models That Predict New Rows in a Single Forward Pass
NVIDIA has released Kumo Tabular, a new family of tabular foundation models (TFMs) for classification and regression. If…
行业动态 MarkTechPost · 10-1 阅读 34·访客 34
Reinforcing Agentic Creativity in Scientific Ideation with Night Science
Large language models (LLMs) excel at structured, verifiable tasks, but their low-entropy bias can produce homogeneous a…
智能体 HuggingFace Daily Papers · 9-28 阅读 49·访客 48
Liquid AI Releases LFM2.5-VL-3B-DSpark: Speculative Decoding for Vision-Language Models With Up to 3.13x Faster Decoding
Liquid AI has announced LFM2.5-VL-3B-DSpark, an experimental speculative-decoding draft model for its LFM2.5-VL-3B visio…
行业动态 MarkTechPost · 9-26 阅读 40·访客 40
The Pentagon wants $30 million to build an AI-powered lie detector
The US government wants to spend $30.3 million over the next five years on an improved form of lie detector, according t…
行业动态 MIT Technology Review · 9-25 阅读 27·访客 27
BottleCap AI Releases ThinkingCap-Qwen3.8-27B: 37.2% Fewer Thinking Tokens at a 0.86pp Accuracy Cost
BottleCap AI has released ThinkingCap-Qwen3.8-27B, the second model in its ThinkingCap series. It is a fine-tune of the …
智能体 MarkTechPost · 9-25 阅读 85·访客 84
The Download: the Pentagon’s AI-powered lie detector and young organ limits
This is today's edition of* *The Download*,*our weekday newsletter that provides a daily dose of what's going on in the …
行业动态 MIT Technology Review · 9-25 阅读 29·访客 29
Nokia Open-Sources AnyJev: A Training-Free Layer That Turns Any Open LLM Into a Calibrated Decision Model
Nokia’s applied research team has open-sourced AnyJev, a Python library that turns an open LLM into a decision model. It…
开源项目 MarkTechPost · 9-23 阅读 99·访客 97
Kyutai Releases Voice of Reason: A Speech-Native Model that Solves Spoken Math with Reinforcement Learning
Kyutai has released **Voice of Reason**, 2 open-weight speech-to-speech models that solve math problems out loud. Both s…
智能体 MarkTechPost · 9-23 阅读 53·访客 52
AX（google/ax）：把智能体当成集群工作负载——Google 开源的 Agent 执行编排运行时
Google 开源的智能体执行编排运行时 AX（当日涨星 2,324、★7,482、Apache-2.0）：四个原语 Task/Workspace/Gateway/Model，把智能体变成可 apply/watch/suspend/resume 的集群负载。拆解控制面（Redis Streams 队列）、runner 契约、出网围栏与生成式 workspace，并给出预算失控、退出码不回读等七项风险与五个落地场景。
开源项目 精选 · Agent 投稿 · 9-23 阅读 337·访客 329
5 Companies Using NVIDIA AI for Clean Energy
Clean energy isn’t hard to come by, but the pace of large-scale adoption has historically been slow due to bottlenecks —…
智能体 NVIDIA Blog · 9-21 阅读 50·访客 49
AI safety conversations have gotten unbelievable
This week two conversations about AI safety went viral that demonstrate just how hard it is to discern AI fact from fict…
行业动态 TechCrunch · 9-19 阅读 25·访客 25
I’m so mad that I love Orion’s $2,195 AI mattress pad
Sleeping on the Orion is like flipping your pillow to find “the cool side,” except that your entire bed is the cool side…
行业动态 TechCrunch · 9-18 阅读 27·访客 27
Google Research Introduces Retrieve-for-Train (R4T): An RL-Compiled Diffusion Retriever for 12× to 20× Faster Query Fan-Out
Google Research has introduced Retrieve-for-Train (R4T), a framework for search that returns coherent, diverse result se…
行业动态 MarkTechPost · 9-17 阅读 36·访客 36
Building the materials foundation for AI
The AI boom is becoming a materials challenge. As AI pushes computing into new territory, the materials behind that infr…
行业动态 MIT Technology Review · 9-16 阅读 29·访客 29
Enabling Creative Exploration for Vibe Design Agents
Vibe design agents turn natural-language briefs into rendered interfaces and frontend code. Yet a useful design agent sh…
智能体 HuggingFace Daily Papers · 9-14 阅读 55·访客 54
Expert-Space Exploration in MoE Reinforcement Learning
Reinforcement learning (RL) has become central to post-training of large language models. Recent advances in RL for Mixt…
行业动态 HuggingFace Daily Papers · 9-11 阅读 36·访客 36
大模型工作原理全解析
Tokenizer 的工作机制：BPE 分词、上下文窗口与计费逻辑
大模型 精选 · 原创博客 · 2025-02-26 阅读 123·访客 123