2025_NIPS_DAPO : Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Ad...

文章核心内容与创新点总结

核心内容

本文提出一种基于直接优势的策略优化(DAPO)算法,专为提升大语言模型(LLMs)的多步推理能力设计。该算法针对现有强化学习(RL)方法在推理任务中面临的奖励稀疏、训练方差高、价值估计不准确等问题,采用离线分步式强化学习框架,通过 Critic 网络提供细粒度的步骤级信号,优化推理过程中的每一步决策,最终在数学和代码任务的多个基准测试中实现性能提升。

创新点
  1. 分步式优化机制:不同于 DPO、GRPO 等响应级方法对整个推理过程统一分配奖励,DAPO 聚焦步骤级优化,为每个中间推理步骤提供独立优势信号,降低训练方差。
  2. Actor-Critic 分离训练:将 Critic 网络训练与 Actor 策略优化分离,先预训练 Critic 以准确估计状态价值,再用于 Actor 优化,避免传统 AC 方法的共训练不稳定性。
  3. 理论保障与离线适配:提供单调改进的理论证明(Theorem 3.2),确保策略迭代过程中性能持续提升;采用离线训练模式,无需在线采样,提升数据效率。
  4. 广泛适用性:在 SFT 模型和已经过 RL 训练的模型上均能有效提升性能,适配数学推理(MATH、GSM8K 等)和代码生成(HumanEval、MBPP 等)多类任务。

翻译部分(Markdown 格式)

船载 OpenHarmony AIS 航海工作台:告警与防碰撞预警系统 船载OpenHarmony AIS航海工作台的告警与防碰撞系统,集成十余类告警(超速、偏航、会遇、SOS等),通过网格空间索引实现高效邻近判定,保障实时性。告警管理器统一调度规则、去重、通知与日志,支持悬浮球、语音、跑马灯、弹窗多渠道触达,确保航行安全。SOS紧急通道独立运行,避免干扰。系统设计强调性能优化与多场景适配,为航海安全提供核心支撑。 阅读详情

相关推荐

AI 应用开发:四维架构落地实战——以 HR Agent 为例拆解感知·推理·记忆·执行【意图路由、规划编排、长期记忆、工具执行、面试题】

本文基于四维架构(感知·推理·记忆·执行),以HR Agent为例,系统拆解大模型应用从“聊天”到“生产可用”的落地路径。通过Spring AI实现意图路由、规划编排、RAG检索与工具调用,结合真实踩坑复盘,揭示架构化设计对安全、成本与可维护性的关键价值,为AI Agent工程化提供可复用的实战框架。

王大师企业官方博客 1206

Unity资源逆向解析:从APK到AssetStudio的完整实战

本文详细介绍了Unity资源逆向解析的全流程,从APK解包到使用AssetStudio深度解析Unity游戏资源。通过实战案例演示如何提取《植物大战僵尸》等游戏的素材,包括贴图、音频和3D模型,帮助开发者掌握Unity游戏逆向工程的核心技术。

weixin_30664051的博客 475

Cursor AI对话历史丢失?开源工具一键恢复项目聊天记录

在软件开发中,数据持久化与工作区管理是保障开发效率与上下文连续性的基础技术。其核心原理在于通过文件系统路径、数据库存储等机制,将应用状态与用户数据持久化关联。对于依赖AI辅助编程的开发者而言,对话历史是宝贵的项目上下文资产,记录了关键的算法思路、API使用范例和问题解决方案。然而,当开发工具(如基于VS Code的Cursor)采用基于项目绝对路径的工作区隔离机制时,项目路径的变更会导致历史对话看似“丢失”,实则是被隔离在了旧路径对应的数据沙箱中。这直接影响了开发体验与知识沉淀的效率。cursor-chat

weixin_26775679的博客 831

谷歌浏览器崩溃排查:闪退、卡死、网页打不开的修复指南

浏览器多进程架构通过进程隔离、GPU加速和扩展沙箱提升网页渲染效率,但配置损坏、扩展冲突、显卡驱动异常或系统资源不足时,常会以闪退、卡死、白屏、内存占用飙升和能上微信却打不开网页等形式暴露。排查价值在于先分层定位系统、进程、配置扩展与网页内容,再用无痕模式、chrome://crashes、chrome://gpu和浏览器任务管理器收集证据,避免盲目重装。对办公、开发运维和日常维护场景,禁用扩展、关闭硬件加速、刷新DNS缓存、重置配置文件乃至干净重装,都是可复用的工程化处置手段。围绕谷歌浏览器崩溃的典型症状

weixin_34138056的博客 426

FreeRtos——10、全局看门狗设计

RTOS 里的看门狗不只是为了证明 CPU 还在动,而是为了证明每个业务逻辑都在按预期的节奏“呼吸”。

qq_40170041的博客 902

基于 YOLOv26 的金属表面缺陷检测系统:智能视觉质检方案

摘要: 基于YOLOv26的金属表面缺陷检测系统采用深度学习技术,实现对划痕、裂纹、腐蚀等8类常见缺陷的自动化检测。系统通过数据增强预处理和YOLOv26模型的高精度识别能力,具备多类别分类、实时推理和强鲁棒性特点,适用于不同金属材质与光照条件。架构包含数据采集、预处理、YOLOv26检测和后处理模块,代码实现采用PyTorch框架,支持训练数据增强与标准化处理,为工业质检提供高效智能解决方案。

一键难忘的博客 591

Python爬虫教程:抓取社交媒体内容(以Facebook和Instagram为例)

为什么抓取社交媒体内容?品牌分析与监测:通过抓取品牌、产品或服务相关的社交媒体数据,可以获得公众对其的评价,识别市场趋势,制定营销策略。情感分析:分析用户在社交平台上的情感倾向,如对某事件、产品、服务的正面或负面情绪。舆情监控:通过抓取大量社交媒体内容,监测公众对热点事件的反应,发现潜在的社会问题。用户行为分析社交媒体的数据类型:帖子和内容:包括用户发布的文本、图片、视频等。用户互动用户信息:包括用户名、粉丝数、关注数等社交信息。社交媒体的反爬虫机制:API限制。

2201_76125261的博客 1340

18|AI 辅助精准测试:让平台会解释、会总结、会推荐

本文介绍 AI 在精准测试平台中的落地方式,包括变更摘要、风险解释、补测建议和报告总结。测试开发工程师。Java 后端开发工程师。质量平台 / DevOps 平台建设者。想了解精准测试落地方法的技术负责人。从报告中提取变更文件、未覆盖行、推荐用例。拼成结构化 JSON。让 AI 生成 200 字质量摘要。把摘要展示在报告顶部。读完本文后,可以复制下面的 Prompt,让 AI 生成一个报告总结练习。你是一名 AI 应用开发专家和测试架构师。

专注 AI 精准测试平台实战落地,分享从代码 Diff 到回归决策的完整工程闭环。主张“先建数据链路,再上 AI 智能”,让测试从“靠经验”走向“基于风险”。 55

基于Cesium的简易淹没分析效果

淹没分析是通过模拟水体扩散过程来评估洪水、海平面上升等情景下可能影响的区域,其核心作用是为防灾减灾、规划设计和风险管理提供科学依据。预测淹没的范围、水深和持续时间,识别高风险区域,帮助政府制定应急预案和疏散路线,减少人员伤亡和财产损失。

星云数海的博客,一个专注GIS十多年的GISer人。 532

IDEA的使用指南

IDEA基于java的使用手册,可以最快速的上手,在使用中不断的丰富自己的使用技巧.

深度学习工具包 DeepLearningToolbox

深度学习工具包Deprecation notice.-----This toolbox is outdated and no longer maintained.There are much better tools available for deep learning than this toolbox, e.g. [Theano](http://deeplearning.net/software/theano/), [torch](http://torch.ch/) or [tensorflow](http://www.tensorflow.org/)I would suggest you use one of the tools mentioned above rather than use this toolbox.Best, Rasmus.DeepLearnToolbox================A Matlab toolbox for Deep Learning.Deep Learning is a new subfield of machine learning that focuses on learning deep hierarchical models of data.It is inspired by the human brain's apparent deep (layered, hierarchical) architecture.A good overview of the theory of Deep Learning theory is[Learning Deep Architectures for AI](http://www.iro.umontreal.ca/~bengioy/papers/ftml_book.pdf)For a more informal introduction, see the following videos by Geoffrey Hinton and Andrew Ng.* [The Next Generation of Neural Networks](http://www.youtube.com/watch?v=AyzOUbkUf3M) (Hinton, 2007)* [Recent Developments in Deep Learning](http://www.youtube.com/watch?v=VdIURAu1-aU) (Hinton, 2010)* [Unsupervised Feature Learning and Deep Learning](http://www.youtube.com/watch?v=ZmNOAtZIgIk) (Ng, 2011)If you use this toolbox in your research please cite [Prediction as a candidate for learning deep hierarchical models of data](http://www2.imm.dtu.dk/pubdb/views/publication_details.php?id=6284)```@MASTERSTHESIS\{IMM2012-06284, author = "R. B. Palm", title = "Prediction as a candidate for learning deep hierarchical models of data", year = "2012",}```Contact: rasmusbergpalm at gmail dot comDirectories included in the toolbox-----------------------------------`NN/` - A library for Feedforward Backpropagation Neural Networks`CNN/` - A library for Convolutional Neural Networks`DBN/` - A library for Deep Belief Networks`SAE/` - A library for Stacked Auto-Encoders`CAE/` - A library for Convolutional Auto-Encoders`util/` - Utility functions used by the libraries`data/` - Data used by the examples`tests/` - unit tests to verify toolbox is workingFor references on each library check REFS.mdSetup-----1. Download.2. addpath(genpath('DeepLearnToolbox'));Example: Deep Belief Network---------------------```matlabfunction test_example_DBNload mnist_uint8;train_x = double(train_x) / 255;test_x = double(test_x) / 255;train_y = double(train_y);test_y = double(test_y);%% ex1 train a 100 hidden unit RBM and visualize its weightsrand('state',0)dbn.sizes = [100];opts.numepochs = 1;opts.batchsize = 100;opts.momentum = 0;opts.alpha = 1;dbn = dbnsetup(dbn, train_x, opts);dbn = dbntrain(dbn, train_x, opts);figure; visualize(dbn.rbm{1}.W'); % Visualize the RBM weights%% ex2 train a 100-100 hidden unit DBN and use its weights to initialize a NNrand('state',0)%train dbndbn.sizes = [100 100];opts.numepochs = 1;opts.batchsize = 100;opts.momentum = 0;opts.alpha = 1;dbn = dbnsetup(dbn, train_x, opts);dbn = dbntrain(dbn, train_x, opts);%unfold dbn to nnnn = dbnunfoldtonn(dbn, 10);nn.activation_function = 'sigm';%train nnopts.numepochs = 1;opts.batchsize = 100;nn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.10, 'Too big error');```Example: Stacked Auto-Encoders---------------------```matlabfunction test_example_SAEload mnist_uint8;train_x = double(train_x)/255;test_x = double(test_x)/255;train_y = double(train_y);test_y = double(test_y);%% ex1 train a 100 hidden unit SDAE and use it to initialize a FFNN% Setup and train a stacked denoising autoencoder (SDAE)rand('state',0)sae = saesetup([784 100]);sae.ae{1}.activation_function = 'sigm';sae.ae{1}.learningRate = 1;sae.ae{1}.inputZeroMaskedFraction = 0.5;opts.numepochs = 1;opts.batchsize = 100;sae = saetrain(sae, train_x, opts);visualize(sae.ae{1}.W{1}(:,2:end)')% Use the SDAE to initialize a FFNNnn = nnsetup([784 100 10]);nn.activation_function = 'sigm';nn.learningRate = 1;nn.W{1} = sae.ae{1}.W{1};% Train the FFNNopts.numepochs = 1;opts.batchsize = 100;nn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.16, 'Too big error');```Example: Convolutional Neural Nets---------------------```matlabfunction test_example_CNNload mnist_uint8;train_x = double(reshape(train_x',28,28,60000))/255;test_x = double(reshape(test_x',28,28,10000))/255;train_y = double(train_y');test_y = double(test_y');%% ex1 Train a 6c-2s-12c-2s Convolutional neural network %will run 1 epoch in about 200 second and get around 11% error. %With 100 epochs you'll get around 1.2% errorrand('state',0)cnn.layers = { struct('type', 'i') %input layer struct('type', 'c', 'outputmaps', 6, 'kernelsize', 5) %convolution layer struct('type', 's', 'scale', 2) %sub sampling layer struct('type', 'c', 'outputmaps', 12, 'kernelsize', 5) %convolution layer struct('type', 's', 'scale', 2) %subsampling layer};cnn = cnnsetup(cnn, train_x, train_y);opts.alpha = 1;opts.batchsize = 50;opts.numepochs = 1;cnn = cnntrain(cnn, train_x, train_y, opts);[er, bad] = cnntest(cnn, test_x, test_y);%plot mean squared errorfigure; plot(cnn.rL);assert(er<0.12, 'Too big error');```Example: Neural Networks---------------------```matlabfunction test_example_NNload mnist_uint8;train_x = double(train_x) / 255;test_x = double(test_x) / 255;train_y = double(train_y);test_y = double(test_y);% normalize[train_x, mu, sigma] = zscore(train_x);test_x = normalize(test_x, mu, sigma);%% ex1 vanilla neural netrand('state',0)nn = nnsetup([784 100 10]);opts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samples[nn, L] = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.08, 'Too big error');%% ex2 neural net with L2 weight decayrand('state',0)nn = nnsetup([784 100 10]);nn.weightPenaltyL2 = 1e-4; % L2 weight decayopts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex3 neural net with dropoutrand('state',0)nn = nnsetup([784 100 10]);nn.dropoutFraction = 0.5; % Dropout fraction opts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex4 neural net with sigmoid activation functionrand('state',0)nn = nnsetup([784 100 10]);nn.activation_function = 'sigm'; % Sigmoid activation functionnn.learningRate = 1; % Sigm require a lower learning rateopts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex5 plotting functionalityrand('state',0)nn = nnsetup([784 20 10]);opts.numepochs = 5; % Number of full sweeps through datann.output = 'softmax'; % use softmax outputopts.batchsize = 1000; % Take a mean gradient step over this many samplesopts.plot = 1; % enable plottingnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex6 neural net with sigmoid activation and plotting of validation and training error% split training data into training and validation datavx = train_x(1:10000,:);tx = train_x(10001:end,:);vy = train_y(1:10000,:);ty = train_y(10001:end,:);rand('state',0)nn = nnsetup([784 20 10]); nn.output = 'softmax'; % use softmax outputopts.numepochs = 5; % Number of full sweeps through dataopts.batchsize = 1000; % Take a mean gradient step over this many samplesopts.plot = 1; % enable plottingnn = nntrain(nn, tx, ty, opts, vx, vy); % nntrain takes validation set as last two arguments (optionally)[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');```[![Bitdeli Badge](https://d2weczhvl823v0.cloudfront.net/rasmusbergpalm/deeplearntoolbox/trend.png)](https://bitdeli.com/free "Bitdeli Badge")

OV9734 DATASHEET,完整规格书

OV9734完整规格书,包括电气参数,尺寸规格,寄存器配置表等

LinePhone3.2.7(android端最新版本) sip客户端

SIP客户端For android:LinePhone3.2.7(最新版本),官网地址:http://www.linphone.org/

上一篇: 2025_NIPS_Bubbleformer: Forecasting Boiling with Transformers
下一篇: 2025_NIPS_ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code
UnknownBody
博客等级 码龄16年 5601粉丝 4744原创
评论
成就一亿技术人!
拼手气红包6.0元
还能输入1000个字符
 
 条评论被折叠 查看
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付:10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

UnknownBody

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值