few-shot learning

Alimama Tech

Apr 23, 2025 · Artificial Intelligence

Distribution-aware Graph Prompt Tuning (DAGPrompT) for Heterophilic Graphs

Distribution‑aware Graph Prompt Tuning (DAGPrompT) tackles the pre‑training/downstream mismatch on heterophilic graphs by jointly applying low‑rank GLoRA adaptation and hop‑specific prompts that recast tasks as link‑prediction, yielding up to 4.79% accuracy gains and an average 2.43% improvement in few‑shot node classification.

Graph Neural NetworksPretrainingPrompt Tuning

0 likes · 9 min read

Distribution-aware Graph Prompt Tuning (DAGPrompT) for Heterophilic Graphs

DevOps

Feb 12, 2025 · Artificial Intelligence

A Comprehensive Guide to Prompt Engineering, RAG, and Optimization Techniques for Large Language Models

This article presents a systematic framework for crafting effective prompts, detailing the universal prompt template, role definition, task decomposition, RAG integration, few‑shot examples, memory handling, and parameter tuning to enhance large language model performance across diverse applications.

AI optimizationLarge Language ModelsPrompt Templates

0 likes · 24 min read

A Comprehensive Guide to Prompt Engineering, RAG, and Optimization Techniques for Large Language Models

DataFunSummit

Jan 28, 2025 · Artificial Intelligence

Few-Shot Learning for Multi-New-Class Scenarios: Challenges, Methodology, and Experimental Evaluation

This article introduces a novel few‑shot learning approach tailored for multi‑new‑class scenarios, discusses its background, problem definition, proposed parallel training framework, hierarchical fine‑tuning method, and presents extensive experiments demonstrating superior performance and computational efficiency.

computer visiondistributed trainingfew-shot learning

0 likes · 10 min read

Few-Shot Learning for Multi-New-Class Scenarios: Challenges, Methodology, and Experimental Evaluation

Xiaohongshu Tech REDtech

Dec 26, 2024 · Artificial Intelligence

Focused Large Language Models are Stable Many-Shot Learners

FocusICL mitigates the reverse‑scaling of in‑context learning by masking irrelevant tokens and applying hierarchical batch attention, cutting attention complexity, and delivering consistent query focus that yields average accuracy gains of about 5 % across multiple LLMs and benchmarks.

FocusICLIn-Context LearningLarge Language Models

0 likes · 16 min read

Focused Large Language Models are Stable Many-Shot Learners

JD Tech Talk

Nov 11, 2024 · Artificial Intelligence

Prompt Engineering: Concepts, Evolution, Techniques, and a Logistics Application Case

This article explains what Prompt Engineering is, traces its development from early command‑based interactions to modern adaptive and multimodal prompting, details various prompting techniques such as zero‑shot, few‑shot, Chain‑of‑Thought, hallucination‑reduction methods, and demonstrates their practical use in a JD Logistics SKU piece‑type classification case with code examples.

AI promptingChain-of-ThoughtLLM applications

0 likes · 26 min read

Prompt Engineering: Concepts, Evolution, Techniques, and a Logistics Application Case

Tencent Cloud Developer

Sep 27, 2024 · Artificial Intelligence

A Comprehensive Prompt Engineering Framework: Universal Templates, RAG, Few‑Shot, Memory, and Automated Optimization

The article presents a universal four‑part prompt template—role, problem description, goal, and requirements—augmented with role definitions, RAG‑based knowledge retrieval, few‑shot examples, memory handling, temperature/top‑p tuning, and automated optimization techniques such as APE, APO, and OPRO, enabling developers to reliably craft high‑quality prompts for LLMs.

AI Prompt OptimizationLarge Language ModelsRAG

0 likes · 26 min read

A Comprehensive Prompt Engineering Framework: Universal Templates, RAG, Few‑Shot, Memory, and Automated Optimization

Tencent Cloud Developer

Jul 30, 2024 · Artificial Intelligence

A Systematic Guide to Prompt Engineering: From Zero to One

This guide walks readers from beginner to proficient Prompt Engineer by outlining the evolution of prompting, introducing a universal four‑component template, and detailing a five‑step workflow—including refinement, retrieval‑augmented generation, chain‑of‑thought reasoning, and advanced tuning techniques—plus evaluation metrics for LLM performance.

AI promptingChain-of-ThoughtLLM optimization

0 likes · 51 min read

A Systematic Guide to Prompt Engineering: From Zero to One

DataFunSummit

Sep 19, 2023 · Artificial Intelligence

Advances in Information Extraction: From PLM to LLM Paradigms at Alibaba DAMO Academy

This article reviews Alibaba DAMO Academy's research on information extraction, covering background concepts, PLM-era extraction paradigms, few‑shot extraction techniques, and the emerging LLM‑era approaches, while also sharing practical insights, benchmark results, and future directions.

Alibaba DAMOInformation ExtractionLarge Language Models

0 likes · 24 min read

Advances in Information Extraction: From PLM to LLM Paradigms at Alibaba DAMO Academy

58 Tech

Aug 25, 2023 · Artificial Intelligence

Voice Cloning Technology in AI Sales Assistant

This article introduces the AI sales assistant from 58.com, detailing its background, a few‑shot voice cloning approach using real dialogue data, multi‑accent naturalness optimization, deployment architecture, and future plans, while evaluating performance metrics and discussing challenges in speech synthesis quality and stability.

AI sales assistantSpeech Synthesisfew-shot learning

0 likes · 19 min read

Voice Cloning Technology in AI Sales Assistant

DataFunSummit

Aug 15, 2023 · Artificial Intelligence

AI Sales Assistant: Few‑Shot Voice Cloning and Multi‑Accent Naturalness Optimization

The article presents 58 Tongcheng AI Lab's AI sales assistant, detailing its background, a few‑shot voice‑cloning pipeline built on real dialogue data, data preprocessing, FastSpeech2‑based acoustic modeling, multi‑accent style transfer, deployment architecture, controllable synthesis parameters, and future research directions.

AI sales assistantFastSpeech2Speech Synthesis

0 likes · 20 min read

AI Sales Assistant: Few‑Shot Voice Cloning and Multi‑Accent Naturalness Optimization

Tencent Cloud Developer

Jul 26, 2023 · Artificial Intelligence

ChatGPT‑Based Prompt Generator for Stable Diffusion AI Art

The project implements a ChatGPT‑powered prompt generator for Stable Diffusion that translates non‑English ideas, crafts concise 50‑word positive prompts with structured modifiers, filters prohibited content, leverages few‑shot examples, and is containerized via Docker, dramatically simplifying AI art creation for beginners and multilingual users.

AI artChatGPTDocker

0 likes · 16 min read

ChatGPT‑Based Prompt Generator for Stable Diffusion AI Art

Tencent Cloud Developer

Jun 28, 2023 · Artificial Intelligence

Prompt Engineering: Fundamentals, Techniques, and Advanced Strategies

Prompt engineering teaches how to craft effective instructions, context, input data, and output formats for large language models, using clear commands, iterative refinement, and advanced methods such as zero‑shot, few‑shot, chain‑of‑thought, Tree of Thoughts, retrieval‑augmented and progressive‑hint prompting to achieve precise, reliable results across diverse tasks.

AIChain-of-ThoughtLarge Language Models

0 likes · 17 min read

Prompt Engineering: Fundamentals, Techniques, and Advanced Strategies

DataFunTalk

Jun 10, 2023 · Artificial Intelligence

Financial Event Analysis and Applications Based on Pre-trained Models

This article introduces the tasks, techniques, and frameworks for financial event analysis using pre‑trained language models, covering unstructured data parsing, event semantics, graph construction, detection, extraction, and prediction, and presents the TDE‑GTEE model that achieves state‑of‑the‑art performance even in few‑shot scenarios.

AIEvent Extractionevent graph

0 likes · 18 min read

Financial Event Analysis and Applications Based on Pre-trained Models

Baidu Geek Talk

Mar 16, 2023 · Artificial Intelligence

PaddleDetection v2.6 Release: PP-YOLOE Family Expansion and Advanced Detection Algorithms

PaddleDetection v2.6 expands the PP‑YOLOE family with rotating, small‑object, dense‑object, and ultra‑lightweight edge‑GPU models, upgrades PP‑Human and PP‑Vehicle toolboxes, releases semi‑supervised, few‑shot and distillation learning methods, adds numerous state‑of‑the‑art algorithms, and improves infrastructure with Python 3.10, EMA filtering and AdamW support.

BaiduModel DistillationPP-YOLOE

0 likes · 14 min read

PaddleDetection v2.6 Release: PP-YOLOE Family Expansion and Advanced Detection Algorithms

DataFunSummit

Feb 19, 2023 · Artificial Intelligence

Understanding In-Context Learning in Large Language Models: Experiments, Analysis, and Theoretical Insights

This article explains the concept of in‑context learning in large language models, presents experimental evaluations such as copy‑output, date‑formatting, and label‑remapping tasks, and discusses a recent theoretical analysis that links attention layers to implicit gradient‑based fine‑tuning, highlighting why model scale and data volume matter.

GPT-3In-Context LearningLarge Language Models

0 likes · 15 min read

Understanding In-Context Learning in Large Language Models: Experiments, Analysis, and Theoretical Insights

DataFunTalk

May 19, 2022 · Artificial Intelligence

Open‑Domain Information Extraction with UIE: Code Samples, Model Details, and Performance Highlights

This article introduces PaddleNLP's UIE tool for open‑domain information extraction, explains its underlying UIE model and ERNIE 3.0 foundation, showcases concise Python code for entity and event extraction, and presents few‑shot and SOTA performance results across multiple IE benchmarks.

Information ExtractionPaddleNLPPython

0 likes · 11 min read

Open‑Domain Information Extraction with UIE: Code Samples, Model Details, and Performance Highlights

DataFunTalk

Apr 21, 2022 · Artificial Intelligence

Solving Cold‑Start in Recommender Systems: The DropoutNet Approach

This article explains why cold‑start is a critical challenge for recommender systems, outlines four practical strategies—generalization, fast data collection, transfer learning, and few‑shot learning—and then details the DropoutNet model, its end‑to‑end training, loss functions, negative‑sampling techniques, and open‑source implementation.

Cold StartDropoutNetembedding

0 likes · 21 min read

Solving Cold‑Start in Recommender Systems: The DropoutNet Approach

DataFunTalk

Oct 12, 2021 · Artificial Intelligence

PaddleNLP v2.1 Release: Taskflow One‑Click NLP, Few‑Shot Learning Enhancements, and 28× Text Generation Acceleration

PaddleNLP v2.1 introduces an industrial‑grade Taskflow for eight NLP scenarios, a three‑line few‑shot learning paradigm that boosts small‑sample performance, and a FasterTransformer‑based inference engine that delivers up to 28‑fold speedup for text generation, all backed by extensive model and algorithm integrations.

Artificial IntelligenceNLPPaddleNLP

0 likes · 7 min read

PaddleNLP v2.1 Release: Taskflow One‑Click NLP, Few‑Shot Learning Enhancements, and 28× Text Generation Acceleration

iQIYI Technical Product Team

Jun 11, 2021 · Artificial Intelligence

iQIYI M2VoC Multi‑Speaker Multi‑Style Voice Cloning Challenge at ICASSP 2021 – Overview and Results

The iQIYI M2VoC competition at ICASSP 2021, the first low‑resource multi‑speaker, multi‑style voice‑cloning challenge, attracted 153 academic and industry teams to tackle few‑shot (100 utterances) and extreme few‑shot (5 utterances) tracks, evaluated by professional listeners, yielding strong innovations and applications while confirming that single‑sample cloning remains unsolved.

AIAudio ProcessingICASSP2021

0 likes · 7 min read

iQIYI M2VoC Multi‑Speaker Multi‑Style Voice Cloning Challenge at ICASSP 2021 – Overview and Results

DataFunTalk

May 9, 2021 · Artificial Intelligence

Few-Shot Learning, Data Augmentation, and Multi‑Task Learning for Safety Modeling in Ride‑Hailing Platforms

This article presents Didi's exploration of few‑shot learning, data‑augmentation, semi‑supervised self‑training and multi‑task learning techniques to address the scarcity of labeled samples in safety and governance scenarios, demonstrating practical solutions and performance gains across various risk‑detection tasks.

AISemi-supervised Learningdata augmentation

0 likes · 15 min read

Few-Shot Learning, Data Augmentation, and Multi‑Task Learning for Safety Modeling in Ride‑Hailing Platforms