beam search | BestHub

Tencent Advertising Technology

Jan 9, 2025 · Artificial Intelligence

Applying Large Language Models to Search Advertising: End‑to‑End Generative Recall and System Optimizations

This report details how large language models (LLMs) were integrated into Tencent's search advertising pipeline—from early extraction‑distillation experiments in 2023 to a 2024 end‑to‑end generative recall architecture—showing significant improvements in relevance, diversity, and revenue through knowledge injection, supervised fine‑tuning, constrained beam‑search decoding, and high‑performance inference services.

AIKnowledge InjectionLLM

0 likes · 11 min read

Applying Large Language Models to Search Advertising: End‑to‑End Generative Recall and System Optimizations

Baidu Geek Talk

Aug 21, 2023 · Artificial Intelligence

Decoding Strategies for Generative Models: Top‑k, Top‑p, Contrastive Search, Beam Search, and Sampling

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

Decoding Strategies for Generative Models: Top‑k, Top‑p, Contrastive Search, Beam Search, and Sampling

Architect

Jul 1, 2023 · Artificial Intelligence

Comprehensive Guide to Text Generation Decoding Strategies with HuggingFace Transformers

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.

HuggingFacebeam searchdecoding strategies

0 likes · 59 min read

Comprehensive Guide to Text Generation Decoding Strategies with HuggingFace Transformers

Tencent Cloud Developer

Jun 1, 2023 · Artificial Intelligence

A Comprehensive Guide to Decoding Strategies for Text Generation with HuggingFace Transformers

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.

HuggingFaceNatural Language Processingbeam search

0 likes · 60 min read

A Comprehensive Guide to Decoding Strategies for Text Generation with HuggingFace Transformers

DaTaobao Tech

Apr 7, 2023 · Artificial Intelligence

Two‑Level Store Recommendation and Experience Optimization in Taobao’s Daily Good Store

Taobao’s Daily Good Store tackles a two‑level recommendation challenge by jointly ranking shops and their items through a dual‑link system enhanced with a novel scatter‑score metric, personalized category scattering via Earth Mover’s Distance, beam‑search optimization, and UI upgrades, delivering higher efficiency, relevance, diversity, and ecosystem health.

beam searche-commercerecommendation system

0 likes · 11 min read

Two‑Level Store Recommendation and Experience Optimization in Taobao’s Daily Good Store

Kuaishou Tech

Oct 21, 2022 · Artificial Intelligence

Real-time Short Video Recommendation on Mobile Devices: System Design, Model Architecture, and Experimental Evaluation

The paper presents a lightweight on‑device re‑ranking system for short‑video recommendation that leverages real‑time user feedback and context‑aware generative ranking, detailing its architecture, feature engineering, beam‑search optimization, and both offline and online experimental results showing significant performance gains.

beam searchcontext-awarefeature engineering

0 likes · 12 min read

Real-time Short Video Recommendation on Mobile Devices: System Design, Model Architecture, and Experimental Evaluation

Youku Technology

Feb 28, 2022 · Artificial Intelligence

Seq2Path: Generating Sentiment Tuples as Paths of a Tree

Seq2Path treats each sentiment tuple as an independent tree path, training with average path loss and decoding via constrained beam search with a discriminative token, achieving state‑of‑the‑art results on five aspect‑based sentiment analysis datasets and deployment in Alibaba Entertainment AI Brain.

ACLInformation ExtractionNatural Language Processing

0 likes · 3 min read

Seq2Path: Generating Sentiment Tuples as Paths of a Tree

DataFunTalk

Nov 10, 2021 · Artificial Intelligence

Learnable Index Structures for Large‑Scale Retrieval: Deep Retrieval Model and Training Methods

This article introduces ByteDance's Deep Retrieval (DR) framework, describing its learnable index structure that aligns embedding training with retrieval objectives, detailing the core model, structure‑loss training via EM and online EM algorithms, beam‑search serving, multi‑task learning, and practical insights from Q&A.

EM algorithmRecommendation systemsbeam search

0 likes · 11 min read

Learnable Index Structures for Large‑Scale Retrieval: Deep Retrieval Model and Training Methods

Alimama Tech

Sep 8, 2021 · Artificial Intelligence

Engineering Optimizations for Large‑Scale Advertising Recall Models: Full‑Cache Scoring and Index Flattening

Alibaba Mama’s advertising platform modernized its Tree‑based Deep Model by introducing a dual‑tower full‑library DNN with aggressive pre‑filtering and custom GPU TopK kernels, and a flattened‑tree model that retains beam search with multi‑head attention, while applying memory‑aware tricks such as attention swapping, softmax approximation, tiled‑matmul splitting, TensorCore batching, INT8 quantization and cache‑resident ad vectors, enabling multi‑fold latency reductions with minimal recall loss.

GPU AccelerationRecommendation systemsTopK

0 likes · 15 min read

Engineering Optimizations for Large‑Scale Advertising Recall Models: Full‑Cache Scoring and Index Flattening

DataFunTalk

Feb 15, 2021 · Artificial Intelligence

Deep Tree Matching (TDM): Evolution and Practice in Large-Scale Retrieval at Alibaba

This article explains Alibaba's Deep Tree Matching (TDM) technology, covering the challenges of large‑scale match retrieval, the progression from classic two‑stage recall to tree‑based indexing, max‑heap tree modeling, beam‑search retrieval, and the joint model‑index learning across TDM 1.0, 2.0, and 3.0, highlighting significant offline and online performance gains and future research directions.

AlibabaRetrievalbeam search

0 likes · 15 min read

Deep Tree Matching (TDM): Evolution and Practice in Large-Scale Retrieval at Alibaba

New Oriental Technology

Feb 1, 2021 · Artificial Intelligence

Neural Machine Translation: Seq2Seq, Beam Search, BLEU, Attention Mechanisms, and GNMT Improvements

This article explains key concepts of neural machine translation, covering Seq2Seq encoder‑decoder models, beam search strategies, BLEU evaluation, various attention mechanisms, and the enhancements introduced in Google's Neural Machine Translation system to improve speed, OOV handling, and translation quality.

BLEUGNMTNLP

0 likes · 11 min read

Neural Machine Translation: Seq2Seq, Beam Search, BLEU, Attention Mechanisms, and GNMT Improvements

Didi Tech

Oct 10, 2020 · Artificial Intelligence

Deep Reinforcement Learning for Route Planning in DiDi Ride‑Hailing

DiDi’s route engine, handling over 40 billion daily requests, replaces static graph algorithms with a deep‑reinforcement‑learning system that first learns intersection decisions via behavior‑cloning LSTM models and then refines them through self‑play Q‑learning, using beam‑search decoding to produce globally optimal, low‑deviation routes for ride‑hailing.

AIDidiRoute Planning

0 likes · 12 min read

Deep Reinforcement Learning for Route Planning in DiDi Ride‑Hailing

DataFunTalk

Sep 4, 2020 · Artificial Intelligence

Beam Search Aware Training for Optimal Tree-Based Retrieval Models

This article presents a comprehensive study of tree-based deep models for large-scale matching, introduces the theoretical framework of optimal tree models, proposes a Beam Search aware training algorithm (BSAT/OTM) to address training-test mismatch, and demonstrates significant recall improvements on Amazon Books and UserBehavior datasets.

beam searchdeep learninglarge-scale matching

0 likes · 23 min read

Beam Search Aware Training for Optimal Tree-Based Retrieval Models

DataFunTalk

Dec 20, 2019 · Artificial Intelligence

AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications

The article presents AutoCross, a system that automatically generates and selects high‑order feature crossings for tabular data using multi‑granularity discretization, beam search, field‑wise logistic regression and successive mini‑batch gradient descent, achieving superior accuracy and efficiency in large‑scale recommendation scenarios.

AutoCrossRecommendation systemsautomatic feature engineering

0 likes · 10 min read

AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications