Tagged articles
Multimodal Retrieval
35 articles · Page 1 of 1
The article explains how Alibaba Cloud EMR Serverless StarRocks converges full-text, scalar, and vector search into a single engine using RRF for score fusion, In-Filter for predicate pushdown into vector search, and Partial Update for column-level annotation writes, reducing data movement and operational complexity.
In-FilterMultimodal RetrievalPaimon
0 likes · 11 min read

Hologres evolves from a real-time data warehouse into an AI data infrastructure, integrating multimodal data via Object Tables and Dynamic Tables, providing AI Functions for hybrid search within SQL, an AI Assistant for automated warehouse operations, and a long-term memory service for cross-session agent recall.
AI FunctionsAgent MemoryAlibaba Cloud
0 likes · 15 min read

The article explains how OpenClaw tackles the bottleneck of information overload in enterprise research by replacing static keyword search with an Agentic Search loop that iteratively understands, plans, executes, and learns, while Agentic Memory captures and reuses findings across sessions, creating a self‑reinforcing research flywheel.
Agentic SearchEnterprise AILLM
0 likes · 12 min read

This article provides an in‑depth technical analysis of Multimodal GraphRAG, covering document parsing pipelines, layout analysis, model comparisons, knowledge‑graph enrichment, multimodal indexing and retrieval, and a systematic comparison of RAG, GraphRAG, and KG‑QA approaches.
GraphRAGMultimodal RetrievalOCR pipeline
0 likes · 23 min read

Alibaba Cloud's EMR Serverless StarRocks Stella 2.2 unifies vector search, full-text search, and AI functions across both internal and lake tables (Paimon, Iceberg, Lance), enabling a single SQL interface for multimodal retrieval, AI-powered analytics, and RAG workloads without data movement.
AI FunctionsMultimodal RetrievalStarRocks
0 likes · 23 min read

UniNote introduces a unified multimodal embedding model that combines representation learning and ranking optimization in a single forward pass, using a two‑stage SFT‑then‑RL training paradigm and Matryoshka Representation Learning to achieve competitive Item‑to‑Item retrieval performance while reducing latency.
Item2ItemMatryoshka Representation LearningMultimodal Retrieval
0 likes · 12 min read

This article presents a comprehensive technical analysis of multimodal GraphRAG, covering document‑intelligent parsing pipelines, multimodal graph index construction, knowledge‑graph‑enhanced chunk linking, various multimodal RAG approaches, their trade‑offs, benchmark results, and future research directions.
GraphRAGMultimodal RetrievalRAG
0 likes · 24 min read

This article analyzes cutting‑edge AI search and recommendation technologies, covering Alibaba Cloud's Agentic RAG architecture, Huawei Noah's LLM‑enhanced recommender evolution, and Baidu's generative ranking model GRAB, each with detailed designs, performance metrics, and real‑world deployment insights.
AI agentsGenerative RankingMultimodal Retrieval
0 likes · 6 min read

The article analyzes recent end‑to‑end speech models, compares four knowledge‑enhancement architectures, evaluates their technical mechanisms, pros and cons, and outlines how these approaches can be applied to the insurance and finance sectors to build real‑time, domain‑aware voice agents.
Knowledge EnhancementMultimodal RetrievalS2S architecture
0 likes · 12 min read

This article provides a comprehensive technical overview of multimodal GraphRAG, detailing document‑intelligence parsing pipelines, layout analysis, OCR‑pipeline vs OCR‑free approaches, knowledge‑graph integration for chunk relationships, multimodal indexing, retrieval‑generation workflows, and a comparative analysis of RAG, GraphRAG, and KG‑QA solutions.
GraphRAGMultimodal RetrievalOCR
0 likes · 23 min read

This article presents a detailed technical walkthrough of multimodal GraphRAG, covering document‑intelligence parsing pipelines, multimodal graph index construction, knowledge‑graph‑driven chunk linking, recent research progress, performance trade‑offs, and practical recommendations for deploying RAG solutions.
GraphRAGMultimodal RetrievalOCR
0 likes · 23 min read

This article reviews cutting‑edge AI search and recommendation techniques—including Alibaba Cloud's Agentic RAG, Huawei Noah's LLM‑enhanced recommendation pipeline, and Baidu's generative ranking model GRAB—detailing their architectural evolution, multimodal retrieval strategies, GPU acceleration, and measured performance gains.
AI searchAgentic RAGGPU acceleration
0 likes · 6 min read

The article explains how Alibaba Cloud's Milvus Embedding Service eliminates the need for self‑hosted embedding models by integrating model inference, vector generation and Milvus indexing into a managed pipeline, dramatically reducing deployment complexity, operational overhead, and time‑to‑value for semantic search, RAG and multimodal retrieval use cases.
Alibaba CloudEmbeddingMilvus
0 likes · 19 min read

This article presents a detailed technical walkthrough of multimodal GraphRAG, covering document‑intelligence parsing pipelines, layout‑analysis models, knowledge‑graph augmentation, multimodal indexing and retrieval, and a comparative analysis of RAG, GraphRAG, and KG‑QA approaches, with concrete examples, model sizes, benchmark scores, and research citations.
GraphRAGMultimodal RetrievalRAG
0 likes · 25 min read


AI WakaMar 26, 2026 · Artificial Intelligence
This guide explains how to assemble NVIDIA's Nemotron Speech, RAG, and Safety models into a low‑latency, secure production AI agent stack, covering performance benchmarks, multimodal retrieval, safety data sets, integration code, and deployment options for cloud, on‑premise, and edge environments.
Edge ComputingMultimodal RetrievalNVIDIA
0 likes · 9 min read

DeepImageSearch introduces a new paradigm that shifts image retrieval from isolated semantic matching to corpus‑level contextual reasoning, supported by the DISBench benchmark and the ImageSeeker framework, revealing that even state‑of‑the‑art multimodal models struggle with multi‑step visual‑history queries.
DISBenchDeepImageSearchImageSeeker
0 likes · 15 min read

This article surveys cutting‑edge AI techniques—including Alibaba Cloud's Agentic RAG for multimodal search, Huawei Noah's LLM‑enhanced recommendation evolution, and Baidu's generative ranking (GRAB) for ads—detailing their architectures, optimization tricks, performance gains, and real‑world deployment results.
AI searchAgentic RAGGPU acceleration
0 likes · 9 min read

BookRAG introduces a hierarchical, structure‑aware indexing method that combines tree‑based document representation with graph‑based entity linking and an agent‑driven retrieval pipeline, achieving up to 71.2% recall improvement on multimodal long‑document benchmarks while cutting token usage and latency dramatically.
Agent RetrievalLLMMultimodal Retrieval
0 likes · 7 min read

Retrv‑R1, a reasoning‑driven multimodal large language model framework, tackles the precision‑efficiency dilemma of universal multimodal retrieval by introducing a two‑stage coarse‑to‑fine pipeline, an information‑compression module, a detail‑inspection mechanism, and a three‑stage training strategy, achieving SOTA performance across accuracy, efficiency, and generalization benchmarks.
EfficiencyGeneralizationMLLM
0 likes · 21 min read

This article explores why many enterprise AI projects fail to deliver value, analyzes the complexity of real‑world AI use cases, and presents a step‑by‑step demo that combines vector, keyword, numeric, and spatial queries using OceanBase as a unified multimodal data store.
Enterprise AILLMLangGraph
0 likes · 15 min read

The article examines the design shift from the traditional 1688 App to the AI‑native 1688 AI App, detailing how AI‑driven interfaces, system prompts, embedding‑based retrieval, multi‑agent routing, and AI gateways transform B2B product discovery, recommendation, and customization.
AI searchB2B e-commerceMultimodal Retrieval
0 likes · 20 min read

This article explains the end‑to‑end implementation of Video RAG in OpenSearch LLM, covering offline parsing, key‑frame extraction, audio transcription, slice creation, multimodal vectorization, hybrid indexing, and online query processing while addressing challenges like recall performance and long‑video efficiency.
ASRKey Frame ExtractionLLM
0 likes · 10 min read

This guide explains how to use Alibaba Cloud Milvus to create a scalable, high‑performance multimodal search system that supports text‑to‑image, image‑to‑image, and cross‑modal queries across various business scenarios, detailing architecture, deployment steps, validation, and resource cleanup.
AIMilvusMultimodal Retrieval
0 likes · 8 min read

The article examines how emerging data‑infrastructure trends, multi‑modal databases like Neon, Supabase, and ClickHouse, and the convergence of OLTP, OLAP, and vector search are reshaping AI workloads, introducing the Data Warebase concept that unifies warehouse and database capabilities to meet modern AI workflow demands.
AIData InfrastructureHTAP
0 likes · 32 min read

This article highlights eight Meituan research papers accepted at CIKM 2024—spanning self‑supervised sequential recommendation, rating‑consistent explanation generation, CTR prediction via recommendation pre‑training, cross‑domain interest transfer, multimodal vector retrieval, design‑aware poster layout, order‑fulfillment cycle‑time forecasting, and delivery‑scope substitution—offering insights from both internal and university collaborations.
AI researchCTR predictionCross‑Domain Recommendation
0 likes · 16 min read

This article explains how HuoLala leverages large language models, multimodal feature integration, and retrieval‑augmented generation to automatically determine responsibility for order cancellations, improving accuracy, explainability, and driver‑user experience.
AIMultimodal RetrievalRAG
0 likes · 10 min read

Meituan’s search advertising has progressed from rule‑based keyword mining to hierarchical recall that partitions traffic and supply, and now to generative recall using large language models, chain‑of‑thought generation, diffusion‑enhanced multimodal vectors, and knowledge distillation, expanding the decision space while tackling compute and ROI challenges.
Generative ModelsMeituanMultimodal Retrieval
0 likes · 19 min read

The article introduces PreFLMR, an open‑source, general‑purpose pre‑trained multimodal retriever that leverages fine‑grained late‑interaction to boost retrieval‑augmented generation for knowledge‑intensive visual tasks, describes its M2KR benchmark, training stages, and strong experimental results across multiple tasks.
AIFLMRKnowledge Retrieval
0 likes · 11 min read

ConaCLIP introduces a fully‑connected knowledge interaction graph to distill large dual‑encoder models into compact ones, enhancing text‑image retrieval accuracy and efficiency on edge devices, with extensive experiments and supervision strategies demonstrating significant gains over existing baselines.
AIConaCLIPDual Encoder
0 likes · 9 min read

The ACL 2023 paper introduces FashionKLIP, an e‑commerce visual‑language model enhanced by a multimodal concept knowledge graph, detailing its automated knowledge graph construction, dual‑stream training strategy, and superior performance on FashionGen retrieval benchmarks compared to state‑of‑the‑art methods.
FashionKLIPMultimodal Retrievale-commerce
0 likes · 10 min read

This article details Baidu's multimodal retrieval architecture, explaining the separation of online and offline services, the design of the Imazon image processing and ingestion platform, its technical indicators, large‑scale streaming and batch pipelines, optimization practices for high throughput, and the underlying content‑relationship engine.
DAGMultimodal RetrievalSystem Optimization
0 likes · 13 min read

This article details Baidu's large‑scale image processing and multimodal retrieval system, describing its offline‑online architecture, massive data ingestion pipeline, ANN search techniques, performance metrics, infrastructure components, and a series of optimizations for throughput, cost, and reliability in a high‑volume streaming environment.
BaiduImazonMultimodal Retrieval
0 likes · 12 min read

The Imazon platform unifies Baidu’s image acquisition, feature extraction, and ANN‑based multimodal retrieval into a cloud‑native, real‑time pipeline that ingests billions of images daily, optimizes storage and GPU usage, reduces message‑queue costs, and ensures high‑throughput, low‑latency search across text, visual, and voice queries.
DAGMultimodal Retrievalcloud-native
0 likes · 13 min read

The second‑place team tackled KDD Cup 2020’s Multimodal Recall challenge by fine‑tuning ImageBERT and LXMERT on query‑image pairs, generating negatives, applying AMSoftmax and multi‑similarity losses, ensembling weighted predictions, and using score‑based post‑processing, boosting NDCG@5 to 0.8352 and powering Meituan’s multimodal search pipeline.
ImageBERTKDD Cup 2020LXMERT
0 likes · 23 min read

The ‘One Name’ team from Nanjing University achieved a MAP of 0.8986 and third place in the iQIYI multimodal video retrieval challenge by fusing official face embeddings with scene features, using channel‑attention‑based video feature fusion, a multimodal SE‑ResNeXt module, and a carefully partitioned model ensemble.
Feature FusionMultimodal RetrievaliQIYI challenge
0 likes · 7 min read
