Tagged articles

14 articles

Page 1 of 1

May 6, 2026 · Artificial Intelligence

Google Boosts Gemma 4 Inference Speed Up to 3× with MTP Drafter and Day‑0 vLLM Support

Google’s new Multi‑Token Prediction (MTP) drafter for Gemma 4 delivers up to three‑fold inference speedups across hardware and frameworks—validated by official benchmarks and independent DGX Spark tests—while preserving identical output quality, and is immediately usable via Hugging Face, vLLM, MLX, Ollama and edge‑device runtimes.

Apple SiliconGemma 4LLM inference

0 likes · 9 min read

Google Boosts Gemma 4 Inference Speed Up to 3× with MTP Drafter and Day‑0 vLLM Support

DataFunSummit

May 5, 2026 · Big Data

A New Data Lake Paradigm: Volcano Engine’s Multi‑Modal Data Lake Built on Lance

The article presents Volcano Engine’s AI‑focused data lake built on the Lance format, detailing why traditional lakes fall short for multimodal data, the engineering enhancements such as Binary Copy Compaction, Lance Insight, distributed vector indexing, JSON‑based tagging, Row‑ID shuffle optimization, and real‑world case studies that demonstrate significant performance and cost gains.

AIBinary Copy CompactionData Lake

0 likes · 18 min read

A New Data Lake Paradigm: Volcano Engine’s Multi‑Modal Data Lake Built on Lance

Xiaohongshu Tech REDtech

Apr 15, 2026 · Artificial Intelligence

How Relax Powers Scalable Multi‑Modal RL Training with Full‑Async Pipelines

Relax, an open‑source reinforcement‑learning engine from Xiaohongshu AI Platform, combines service‑oriented fault‑tolerant architecture, a distributed checkpoint service, and an asynchronous training pipeline to achieve up to 76% speed‑up and near‑zero overhead for multi‑modal RL workloads.

Asynchronous PipelineDistributed TrainingRay Serve

0 likes · 10 min read

How Relax Powers Scalable Multi‑Modal RL Training with Full‑Async Pipelines

DataFunSummit

Mar 2, 2026 · Artificial Intelligence

How Data-Juicer Powers Multi‑Modal Data Processing for Large Language Models

This article explains the evolution of Data‑Juicer from a pure‑text preprocessing tool to a full‑stack multi‑modal data engine, detailing its architecture, operator library, Ray‑based distributed execution, performance benchmarks, integration with AI agents, and roadmap for future AI‑centric data workflows.

Data-JuicerRaydata-processing

0 likes · 31 min read

How Data-Juicer Powers Multi‑Modal Data Processing for Large Language Models

AI Frontier Lectures

Dec 17, 2025 · Artificial Intelligence

Can OmniVGGT Unlock Multi‑Modal 3D Vision with Any Number of Inputs?

OmniVGGT introduces a flexible omni‑modality driven transformer that can ingest arbitrary numbers of geometric cues such as depth maps and camera parameters, achieving state‑of‑the‑art performance on diverse 3D tasks while keeping inference speed comparable to its RGB‑only predecessor.

3D visionGeometryOmniVGGT

0 likes · 13 min read

Can OmniVGGT Unlock Multi‑Modal 3D Vision with Any Number of Inputs?

Bilibili Tech

Jan 21, 2025 · Artificial Intelligence

Accelerating Large Model Inference: Challenges and Multi‑Level Optimization Strategies

The article outlines how exploding LLM sizes create compute, memory, and latency bottlenecks and proposes a full‑stack solution—operator fusion, high‑performance libraries, quantization, speculative decoding, sharding, contiguous batching, PageAttention, and specialized frameworks like MindIE‑LLM—to dramatically boost inference throughput and reduce latency, while highlighting future ultra‑low‑bit and heterogeneous hardware directions.

Continuous BatchingHardware OptimizationInference Acceleration

0 likes · 21 min read

Accelerating Large Model Inference: Challenges and Multi‑Level Optimization Strategies

Sohu Tech Products

Nov 27, 2024 · Artificial Intelligence

RAG Technology and Practical Application in Multi-Modal Query: Using Chinese-CLIP and Redis Search

The article explains how Retrieval‑Augmented Generation (RAG) outperforms direct LLM inference by enabling real‑time knowledge updates and lower costs, and demonstrates a practical multi‑modal RAG pipeline that uses Chinese‑CLIP for vector encoding, various chunking strategies, and Redis Search for fast vector storage and retrieval.

Chinese-CLIPLLMRAG

0 likes · 17 min read

RAG Technology and Practical Application in Multi-Modal Query: Using Chinese-CLIP and Redis Search

AntTech

Oct 30, 2023 · Artificial Intelligence

AntM2C: A Large-Scale Multi‑Scenario Multi‑Modal CTR Prediction Dataset from Alipay

AntM2C is a publicly released, billion‑sample click‑through‑rate (CTR) dataset covering five distinct Alipay business scenarios, providing both ID and rich multi‑modal (text and image) features to enable comprehensive evaluation of multi‑scenario, cold‑start, and multi‑modal CTR models at industrial scale.

CTRlarge scalemulti-modal

0 likes · 14 min read

AntM2C: A Large-Scale Multi‑Scenario Multi‑Modal CTR Prediction Dataset from Alipay

DataFunTalk

Jan 21, 2023 · Artificial Intelligence

Challenges and Best Practices in Recommendation Systems – Expert Interview

This interview with three recommendation‑system experts explores the technical architecture, data sources, feature engineering, recall and ranking strategies, evaluation metrics, cold‑start solutions, and practical difficulties, offering actionable insights to avoid common pitfalls in real‑world recommender deployments.

Evaluation MetricsRecommendation Systemscold start

0 likes · 15 min read

Challenges and Best Practices in Recommendation Systems – Expert Interview

Hulu Beijing

Aug 19, 2022 · Artificial Intelligence

Disney’s M5 Model: Multi‑Modal, Multi‑Interest, Multi‑Scenario Boost for Streaming Recommendations

Disney’s Content Discovery team introduces M5, a multi‑modal, multi‑interest, multi‑scenario recall model that enhances VOD and live streaming recommendations by leveraging rich metadata, user behavior, and contextual features, outperforming baseline methods with significant hit‑ratio gains across Hulu and Disney+.

Deep LearningM5 modelRecommendation Systems

0 likes · 22 min read

Disney’s M5 Model: Multi‑Modal, Multi‑Interest, Multi‑Scenario Boost for Streaming Recommendations

Alimama Tech

Jun 15, 2022 · Artificial Intelligence

Multi-modal Multi-query Search Session Modeling with Heterogeneous Graph Neural Networks

The paper introduces MUVCOG, a heterogeneous graph neural network that models multi‑modal, multi‑query search sessions on Mobile Taobao by jointly learning attention‑based global and hierarchical local views through contrastive pre‑training, yielding universal session embeddings that markedly improve CTR prediction, query recommendation, and intent classification.

Graph Neural Networkcontrastive learningmulti-modal

0 likes · 15 min read

Multi-modal Multi-query Search Session Modeling with Heterogeneous Graph Neural Networks

DataFunSummit

Jan 19, 2022 · Artificial Intelligence

Feizhu Information Flow Content Recommendation: Architecture, Cold-Start Strategies, Multi-Modal Understanding, and Ranking Mechanisms

This article presents a comprehensive overview of Feizhu's information‑flow recommendation system, detailing its mixed‑material architecture, cold‑start recall and coarse‑ranking techniques, multi‑modal pre‑training and fine‑tuning, fine‑ranking with user‑state gating, and tiered traffic‑flow mechanisms for content delivery.

Travelcold startcontent recommendation

0 likes · 17 min read

Feizhu Information Flow Content Recommendation: Architecture, Cold-Start Strategies, Multi-Modal Understanding, and Ranking Mechanisms

DataFunSummit

Oct 10, 2021 · Artificial Intelligence

Advances in Knowledge Graph Construction and Applications at Alibaba's AliMe

This article presents Alibaba's AliMe team’s year‑long progress on knowledge graphs, covering the basics of knowledge graphs, domain‑specific and multi‑modal graph construction techniques, practical e‑commerce applications such as dialogue‑driven recommendation, virtual‑anchor script generation, and key takeaways for future research.

Knowledge Graphartificial intelligenceentity extraction

0 likes · 24 min read

Advances in Knowledge Graph Construction and Applications at Alibaba's AliMe

Meituan Technology Team

Dec 3, 2020 · Artificial Intelligence

Meituan Knowledge Graph Group's Six Papers Accepted at CIKM 2020

Meituan’s search and NLP team announced that six knowledge‑graph papers—covering query‑aware tip generation, BERT‑based ranking, multi‑modal and sequential recommendation, conversational recommendation, and graph‑embedding for personalized product search—were accepted at CIKM 2020, resulting from university collaborations and already deployed to boost Meituan’s search, recommendation and product‑search services.

BERTCIKM 2020Knowledge Graph

0 likes · 13 min read

Meituan Knowledge Graph Group's Six Papers Accepted at CIKM 2020