RAG in the Long-Context Era: Challenges, Benchmarks, and Context Engineering

The article analyzes how expanding LLM context windows to millions of tokens reshape Retrieval‑Augmented Generation, detailing chunking trade‑offs, embedding retrieval limits, attention U‑shaped distribution, benchmark results, and the emerging practice of Context Engineering for optimal end‑to‑end pipelines.

BenchmarkingEmbedding RetrievalLLM

0 likes · 10 min read

RAG in the Long-Context Era: Challenges, Benchmarks, and Context Engineering

DataFunTalk

Sep 29, 2025 · Artificial Intelligence

How Glint-MVT Powers City‑Scale Multimodal AI: Insights from a Tech VP

In an interview before the DACon conference, Dr. Feng Ziyong reveals how Glint‑MVT and novel data‑synthesis techniques overcome distribution gaps, improve compositional understanding, and enable billion‑scale, second‑level retrieval for city‑level surveillance, while balancing model efficiency and effectiveness.

Embedding RetrievalMultimodal AIcity surveillance

0 likes · 11 min read

How Glint-MVT Powers City‑Scale Multimodal AI: Insights from a Tech VP

Architect

Jan 12, 2024 · Artificial Intelligence

Can Divide‑and‑Conquer Boost Embedding‑Based Retrieval in Recommenders?

The article reviews the arXiv paper “Divide and Conquer: Towards Better Embedding‑based Retrieval for Recommender Systems from a Multi‑task Perspective”, explaining how grouping candidates, balancing easy and hard negatives, and using multi‑interest user vectors can improve recall performance in large‑scale recommendation pipelines.

Embedding Retrievaldivide and conquerindustry insights

0 likes · 7 min read

Can Divide‑and‑Conquer Boost Embedding‑Based Retrieval in Recommenders?

Kuaishou Tech

Apr 24, 2023 · Artificial Intelligence

Divide‑and‑Conquer Embedding‑Based Retrieval with Prompt‑Based Multi‑Task Learning for Large‑Scale Recommendation

This paper identifies the trade‑off between simple and hard negatives in embedding‑based retrieval for recommendation, proposes a clustering‑based divide‑and‑conquer framework combined with prompt‑driven multi‑task learning to improve relevance, diversity, and fairness, and validates the approach through offline metrics, online A/B tests, and comparative experiments.

Embedding RetrievalPrompt Tuningapproximate nearest neighbor

0 likes · 9 min read

Divide‑and‑Conquer Embedding‑Based Retrieval with Prompt‑Based Multi‑Task Learning for Large‑Scale Recommendation

DataFunSummit

Jul 25, 2021 · Artificial Intelligence

Advances in Query Understanding and Semantic Retrieval at Zhihu Search

This article details Zhihu Search's engineering solutions for long‑tail query challenges, covering historical development, term weighting, synonym expansion, query rewriting with reinforcement learning, and semantic recall using BERT‑based models, while also outlining future research directions such as GAN‑based rewriting and lightweight pre‑training.

BERTEmbedding RetrievalQuery Rewriting

0 likes · 14 min read