Tagged articles
text generation
42 articles · Page 1 of 1
Researchers from City University of Hong Kong, Shenzhen University, USTC, and Oxford propose Seq-Drifting, a context-dependent drifting field method enabling one-step text generation for diffusion language models, achieving 11.2x speedup over 4-step baselines with Gen-PPL of 36.01 on 128-token generation, and validated on translation, summarization, and reasoning tasks.
Seq-Driftingcontext-dependent drifting fielddiffusion language models
0 likes · 11 min read

Anthropic’s FAQ explains that Claude’s invisible watermark, built on DeepMind’s SynthID‑Text method, replaces the model’s random seed with a key‑driven deterministic source, leaving output quality unchanged while making long‑form text detectable but short or factual passages hard to trace.
AIClaudeDeepMind
0 likes · 7 min read

The author walks through integrating Agnes AI's free text, image, and video models with Claude Code via CC Switch, details each setup step, runs real‑world tasks such as codebase analysis, webpage generation, diagram creation, and short‑video production, and evaluates the models' capabilities and limitations.
API integrationAgnes AIClaude Code
0 likes · 15 min read

Google’s open‑source DiffusionGemma model leverages a 26‑billion‑parameter Mixture‑of‑Experts architecture and discrete diffusion decoding to generate whole text blocks, achieving up to four times faster generation—over 1100 tokens/s on an NVIDIA H100 and 700 tokens/s on an RTX 5090—while activating only 3.8 billion parameters during inference.
DiffusionGemmaDiscrete DiffusionGPU acceleration
0 likes · 4 min read

This article introduces the basics of Natural Language Processing, covering core tasks such as language understanding and generation, common applications, essential linguistic analyses, environment setup with Python libraries, hands‑on code examples for preprocessing, POS tagging, NER, sentiment analysis using both classical and transformer models, text generation with GPT‑2, and discusses challenges and Rust‑centric integration strategies.
NLPPythonRust
0 likes · 13 min read

The Qwen 3.7‑Max and Qwen 3.7‑Plus preview models debut with top‑15 global rankings in Arena, the only Chinese models in text and vision leaderboards, while a timeline analysis shows the Qwen series accelerating from 4‑6‑month releases to a 2‑3‑month cadence and introducing dense and MoE variants up to 235 B parameters.
AI benchmarkChinese AIModel Iteration
0 likes · 6 min read

The article explains three practical prompting techniques—periodic core requirement restatement, repeated inclusion of the original text, and multiple task repetitions—that help large language models maintain focus, avoid missing details, and produce deeper, more accurate outputs in long‑context and multi‑rule scenarios, with concrete examples.
AI ProductivityLLM promptingtext generation
0 likes · 33 min read

A recently leaked briefing on OpenAI’s upcoming GPT‑5.4 suggests the model will dramatically improve both pure text generation and seamless multimodal interaction, a move that not only pushes technical limits but also reshapes the AI competitive landscape, raising new ethical, privacy, and market‑structure concerns.
AI competitionGPT-5.4ethical concerns
0 likes · 6 min read

This tutorial revisits a simple text‑generation function, explains how temperature scaling and top‑K sampling reshape token probability distributions, demonstrates their effects with PyTorch code and visualizations, and shows how to integrate both techniques into an improved generation routine for more diverse and human‑like outputs.
LLMPyTorchtemperature scaling
0 likes · 13 min read

The article compares autoregressive and diffusion language models, detailing their mathematical foundations, training and inference pipelines, performance trade‑offs such as speed, coherence and diversity, and explores hybrid approaches and emerging research directions for more efficient and controllable text generation.
AI researchHybrid ModelsTransformer
0 likes · 17 min read

MarkerGen introduces a novel, plug‑and‑play framework that decomposes length‑controllable text generation into four sub‑abilities—identifying, counting, planning, and aligning—integrates external tokenizers and dynamic markers, and achieves significantly lower length errors and higher quality across diverse models, tasks, and languages.
LLMLength-Controlled GenerationMarkerGen
0 likes · 14 min read

This article explores how high‑quality content assets—text, images, and video—drive SEO and user engagement, then delves into the challenges of crafting push‑notification copy and presents an intelligent copy system that uses template and keyword generation, transformer models, BLEU and semantic similarity evaluation, and various sampling strategies to improve relevance and diversity.
AIEvaluation MetricsNLP
0 likes · 30 min read

The article analyzes Mercury Coder, a diffusion‑based language model that generates text and code in parallel, compares its speed and quality against traditional autoregressive LLMs like GPT‑4o‑mini using a ball‑collision benchmark, and discusses the underlying score‑entropy training, current limitations, and future multimodal potential.
AI performanceMercurybenchmark
0 likes · 8 min read


JavaEdgeMar 16, 2025 · Artificial Intelligence
This article explains the core principles, implementation steps, and practical challenges of using multi‑language back‑translation to enrich text data, provides Python code for a configurable augmentation pipeline, showcases e‑commerce and financial use cases, and presents evaluation metrics that demonstrate significant gains in semantic fidelity and model performance.
NLPPythonback-translation
0 likes · 9 min read

This article introduces how to use the JavaScript library transformers.js directly in the browser, leveraging Google’s built‑in window.ai models, outlines supported AI tasks, demonstrates a live demo, and provides the core implementation code for model loading, worker communication, and text generation.
Transformers.jsWeb Workersbrowser-ai
0 likes · 5 min read

This tutorial introduces Spring AI and Spring Cloud Alibaba AI, explains their core features, shows how to set up a Maven project with the required dependencies, and provides step‑by‑step code examples for invoking text, image, and audio generation models using Spring Boot.
AI integrationImage GenerationJava
0 likes · 9 min read

This article presents a comprehensive overview of how knowledge graphs are integrated into e‑commerce AIGC pipelines, covering domain‑specific and generic KG‑driven text generation, model architecture, controllable generation techniques, experimental results, and future directions for large language models in commercial settings.
AIAIGCControlled Generation
0 likes · 23 min read

This article presents a comprehensive overview of how knowledge graphs are leveraged in e‑commerce AIGC pipelines, detailing domain‑specific and general graph‑based text generation, model architecture, controllable generation techniques, experimental results, and future directions for large language model integration.
AIGCdomain adaptatione-commerce
0 likes · 22 min read

This review of the recent MindSpore NLP public class walks through the fundamentals of large language model text generation, detailing deterministic decoding such as greedy and beam search, stochastic sampling techniques like temperature, top‑k and top‑p, and advanced methods including constrained beam, contrastive, and assisted search, with illustrative examples.
Greedy SearchLLMMindSpore
0 likes · 5 min read

The article explains how generative models use deterministic methods like greedy and beam search and stochastic techniques such as top‑k, top‑p, contrastive search and sampling, describing their mechanisms, temperature control, repetition penalties, and practical trade‑offs for balancing fluency, diversity and coherence.
AIbeam searchcontrastive search
0 likes · 9 min read


ArchitectJul 1, 2023 · Artificial Intelligence
This tutorial explores various text generation decoding methods—including greedy search, beam search, top‑k/top‑p sampling, sample‑and‑rank, and group beam search—explaining their principles, providing detailed Python code examples, and comparing their use in modern large language models.
Greedy SearchHuggingFaceTransformers
0 likes · 59 min read

This article reviews the rapidly evolving field of structured‑data text generation, covering AI development stages, core concepts, model architectures from pipeline to pretrained transformers, key challenges such as content selection, numeric representation, reasoning and style control, and outlines recent research directions and Q&A insights.
AIPretrained Modelsnumeric reasoning
0 likes · 21 min read

This guide thoroughly explains the major decoding strategies for neural text generation in HuggingFace Transformers—including greedy, beam, diverse beam, sampling, top‑k, top‑p, sample‑and‑rank, beam sampling, and group beam search—detailing their principles, Python implementations with LogitsProcessor components, workflow diagrams, comparative analysis, and references to original research.
HuggingFaceTransformersbeam search
0 likes · 60 min read

Airbnb replaced its XLM‑RoBERTa ranking with an MT5 encoder‑decoder for content recommendation, built a real‑time generative assistant for reply suggestions and intent detection, and deployed a T5‑based paraphrase chatbot, showing that large‑scale pre‑trained transformers improve relevance, agent efficiency, and user satisfaction.
AIAirbnbCustomer Support
0 likes · 12 min read

This article surveys the evolution of AI‑generated content for intelligent writing, covering its definition, key technologies from RNN Seq2Seq to Transformer‑based models such as UniLM, T5, BART and GPT series, evaluation datasets and metrics, product deployments by Datagrand, and the remaining challenges and future directions.
AI writingAIGCGPT
0 likes · 25 min read

The article surveys automatic advertising copy generation, detailing why optimization is needed, the fundamentals of neural text generation with Seq2Seq and attention, extractive versus abstractive approaches, modern embeddings and MASS pre‑training, practical data and evaluation methods, and future enhancements such as multi‑stage attention, knowledge integration, and large pre‑trained models.
AIAdvertisingMASS
0 likes · 21 min read

This article reviews the integration of contrastive learning into text generation, explains why it helps mitigate exposure bias, introduces the CoNT framework with three key improvements, presents extensive experiments on translation, summarization, code comment and data‑to‑text tasks, and discusses practical deployment considerations.
AICoNTContrastive Learning
0 likes · 21 min read

Alibaba’s advertising AI team presents a comprehensive study of four new multimodal copywriting tasks—image overlay text generation, video narration, text style transfer, and detail-page extraction—detailing model architectures, training on billions of images, experimental results, and practical deployment in the “Xiyu” product.
advertising copydetail extractionlarge-scale training
0 likes · 17 min read

Alibaba’s advertising team introduces CREATER, a CTR‑driven text generator that leverages user reviews, aspect control codes, and contrastive fine‑tuning, and CONNA, a non‑autoregressive bundle creator that predicts heterogeneous ad elements with set‑based loss, both delivering substantial online CTR gains and CPC reductions through dynamic creative optimization.
CTRContrastive LearningDynamic creative optimization
0 likes · 25 min read

This article presents a comprehensive overview of the challenges in e‑commerce product copy generation, introduces a unified framework comprising a copy generation system, a copy‑cleaning subsystem, and a quality evaluation module, and details practical optimization techniques applied to short and long copy scenarios.
AIdata cleaningmodel optimization
0 likes · 17 min read

This article explores why AI‑to‑AI dialogue is needed, outlines the overall architecture of an AI conversation system, details text‑generation and voice‑synthesis techniques, and examines how such technology can power immersive metaverse social experiences, illustrated with the XiaoIce Island platform.
AI conversationDialogue SystemsMetaverse
0 likes · 21 min read

The article explains how rapid internet growth created information overload, leading to concise summary services, and how recent AI advances—especially large language models like GPT‑3—enable platforms such as JD.com to automatically generate high‑quality, multimodal product copy that drives sales and supports diverse creative tasks.
AINLPe‑commerce
0 likes · 4 min read

This talk presents DAMO Academy’s end‑to‑end NLG pipeline for e‑commerce, detailing the XGeneration content‑reproduction system, controllable short‑text generation models (PKM and PSCN), knowledge‑graph‑to‑text generation, metaphor generation, and their extensions to short‑video script creation and intelligent video editing, together with performance results and practical applications.
Metaphor GenerationNLGVideo Script
0 likes · 12 min read

This talk presents DAMO Academy’s end‑to‑end NLG pipeline for e‑commerce, covering the XGeneration content‑reproduction system, controllable short‑text generation models (PKM, PSCN), KG‑to‑text conversion, metaphor generation, and new‑media extensions such as short‑video script creation and intelligent video editing, together with experimental results and practical applications.
AIDAMO AcademyMetaphor Generation
0 likes · 11 min read


58 TechMar 5, 2021 · Artificial Intelligence
This article presents a comprehensive study on generating recruitment job titles by combining a rule‑based pipeline with advanced seq2seq models—including BiLSTM‑Attention, Pointer‑Generator, and a Field‑Gate Dual‑Attention architecture—demonstrating significant performance gains on real‑world hiring data.
NLPPipelinePointer-Generator
0 likes · 14 min read

The article reviews the principles of popular pretrained language models, compares their architectures, and details how NetEase Yanxuan applied BERT, GPT and ELMo to classification, matching, sequence labeling and generation tasks, presenting experimental results and deployment insights.
BERTNLPpretrained language models
0 likes · 20 min read

This article reviews the evolution of encoder‑decoder based text generation, covering classic seq2seq with attention, pointer networks, copy mechanisms, knowledge‑enhanced models, convolutional approaches, and the latest Transformer‑based pre‑training such as MASS, highlighting their architectures, key innovations, and practical considerations.
NLPSeq2Seqcopy mechanism
0 likes · 17 min read

This tutorial walks you through building a lightweight web application that uses OpenAI's GPT‑2 model to generate text, covering environment setup, model loading, a custom prediction function, and an interactive Panel‑based UI with callbacks, all in less than fifty lines of code.
GPT-2PanelPython
0 likes · 11 min read

This article details Ctrip's AI‑driven Marco Polo platform, describing how large‑scale NLP pipelines combine extraction, richness evaluation, semantic matching and deep‑learning generation (CopyNet, TA‑seq2seq) to produce high‑quality recommendation reasons across multiple product scenarios.
Content ExtractionNLPSpark
0 likes · 16 min read

This article introduces KOBE, a knowledge‑based personalized text generation system that leverages Transformer architecture, attribute fusion, and external knowledge graphs to produce fluent, domain‑aware recommendation reasons for e‑commerce products, with a case study on the Spring Festival cloud theme.
PersonalizationTransformerknowledge graph
0 likes · 13 min read

Meituan’s information flow content team leverages advanced text‑generation techniques—including extractive and generative models, context‑aware representations, and Seq2Seq with attention—to overcome creative constraints, improve evaluation, and boost business metrics such as click‑through rates and user engagement through optimized titles and merchant copywriting.
AIInformation FlowMeituan
0 likes · 32 min read


21CTOJul 5, 2017 · Artificial Intelligence
This article examines how deep‑learning‑based AI models, from symbolic and statistical NLP methods to Karpathy's recurrent network, progressively learn to generate Chinese wuxia novels, poetry, and web fiction, revealing both their surprising advances and inherent limitations.
AIdeep learninglanguage models
0 likes · 15 min read
