---
title: "AlphaSignal Retrieval News"
url: "https://alphasignal.ai/topic/retrieval"
description: "Latest AI and machine learning news about Retrieval on AlphaSignal."
---

# AlphaSignal Retrieval News

Latest AI and machine learning news about Retrieval on AlphaSignal.

## Articles

- [DigUp Brings On-Device Multimodal File Search to Apple Silicon Macs](https://alphasignal.ai/news/digup-brings-on-device-multimodal-file-search-to-apple-silicon-macs.md) (2026-10-10)
- [E5-base Pushes Users to E5-base-v2 With 5-Point Accuracy Gains](https://alphasignal.ai/news/e5-base-pushes-users-to-e5-base-v2-with-5-point-accuracy-gains.md) (2026-10-10)
- [MIT and ETH Zurich Bridge Vision and Language AI Without Paired Training Data](https://alphasignal.ai/news/mit-and-eth-zurich-bridge-vision-and-language-ai-without-paired-training-data.md) (2026-10-10)
- [Jina's jina-embeddings-v5-omni-small Searches Images and Audio Without Re-Embedding Text](https://alphasignal.ai/news/jina-s-jina-embeddings-v5-omni-small-searches-images-and-audio-without-re.md) (2026-10-09)
- [Intelligent Internet's Evoke Brings Hybrid Search Inside PostgreSQL Without Extra Services](https://alphasignal.ai/news/intelligent-internet-s-evoke-brings-hybrid-search-inside-postgresql-without.md) (2026-10-08)
- [Perplexity's pplx-embed-v2-late Searches 190M Docs Without OCR or Chunking](https://alphasignal.ai/news/perplexity-s-pplx-embed-v2-late-searches-190m-docs-without-ocr-or-chunking.md) (2026-10-07)
- [LlamaIndex's OpenDocRouter Puts 10 Document Parsers Behind One API](https://alphasignal.ai/news/llamaindex-s-opendocrouter-puts-10-document-parsers-behind-one-api.md) (2026-10-07)
- [LightOn Releases LightOnOCR-3 to Parse Documents Without Extra Tools](https://alphasignal.ai/news/lighton-releases-lightonocr-3-to-parse-documents-without-extra-tools.md) (2026-10-07)
- [Developers Are Rediscovering e5-small-v2's 33M-Parameter Search Power](https://alphasignal.ai/news/developers-are-rediscovering-e5-small-v2-s-33m-parameter-search-power.md) (2026-10-07)
- [Snowflake's Arctic Embed L Beats OpenAI and Google at Semantic Search](https://alphasignal.ai/news/snowflake-s-arctic-embed-l-beats-openai-and-google-at-semantic-search.md) (2026-10-07)
- [Google DeepMind's EmbeddingGemma 2 Searches Audio, Video, and Images on Your Phone](https://alphasignal.ai/news/google-deepmind-s-embeddinggemma-2-searches-audio-video-and-images-on-your-phone.md) (2026-10-06)
- [Extend's Jevbox Ditches Vector Search, Routes Documents Through a Tree](https://alphasignal.ai/news/extend-s-jevbox-ditches-vector-search-routes-documents-through-a-tree.md) (2026-10-05)
- [Stanford's ScholarCatalyst Reveals AI Misses 52% of Key Research Papers](https://alphasignal.ai/news/stanford-s-scholarcatalyst-reveals-ai-misses-52-of-key-research-papers.md) (2026-10-01)
- [Perplexity's pplx-embed-v2 Beats Voyage at 8x Smaller Vector Size](https://alphasignal.ai/news/perplexity-s-pplx-embed-v2-beats-voyage-at-8x-smaller-vector-size.md) (2026-09-30)
- [Cohere's Embed 5 Lets Developers Index Smart but Query 2.4x Faster](https://alphasignal.ai/news/cohere-s-embed-5-lets-developers-index-smart-but-query-2-4x-faster.md) (2026-09-30)
- [Hugging Face's ELECTRA Reranker Adds ONNX and OpenVINO for Faster CPU Search](https://alphasignal.ai/news/hugging-face-s-electra-reranker-adds-onnx-and-openvino-for-faster-cpu-search.md) (2026-09-30)
- [Google DeepMind's EmbeddingGemma 2 Searches Text, Video and Audio From One 485MB Model](https://alphasignal.ai/news/google-deepmind-s-embeddinggemma-2-searches-text-video-and-audio-from-one-485mb.md) (2026-09-29)
- [Renmin University's EvoOntology Stops Data Agents From Relearning SQL Context Every Task](https://alphasignal.ai/news/renmin-university-s-evoontology-stops-data-agents-from-relearning-sql-context.md) (2026-09-29)
- [Jina AI's jina-reranker-v3 Ranks 64 Documents Together in One Pass](https://alphasignal.ai/news/jina-ai-s-jina-reranker-v3-ranks-64-documents-together-in-one-pass.md) (2026-09-27)
- [Hugging Face's stsb-bert-tiny Packs a Full Embedding Stack Into 17.6 MB](https://alphasignal.ai/news/hugging-face-s-stsb-bert-tiny-packs-a-full-embedding-stack-into-17-6-mb.md) (2026-09-25)
- [Naver's SPLADE Model Hits 878K Downloads Doubling BM25 Search Accuracy](https://alphasignal.ai/news/naver-s-splade-model-hits-878k-downloads-doubling-bm25-search-accuracy.md) (2026-09-25)
- [Perplexity's Photon Slashes Search Latency by 12x for AI Agents](https://alphasignal.ai/news/perplexity-s-photon-slashes-search-latency-by-12x-for-ai-agents.md) (2026-09-24)
- [Parallel Web Systems Lets AI Agents Query Crunchbase and PubMed Directly](https://alphasignal.ai/news/parallel-web-systems-lets-ai-agents-query-crunchbase-and-pubmed-directly.md) (2026-09-24)
- [You.com Adds One API Flag That Boosts Search Accuracy by 20%](https://alphasignal.ai/news/you-com-adds-one-api-flag-that-boosts-search-accuracy-by-20.md) (2026-09-23)
- [TopK Releases topk-embed-v1 to Slash Visual Document Search Storage Costs](https://alphasignal.ai/news/topk-releases-topk-embed-v1-to-slash-visual-document-search-storage-costs.md) (2026-09-23)
- [Exa Snapshot Lets AI Search the Web as It Existed Years Ago](https://alphasignal.ai/news/exa-snapshot-lets-ai-search-the-web-as-it-existed-years-ago.md) (2026-09-17)
- [Linkup's SPARSEUP Beats Every Sub-150M Sparse Search Model With a 56.4 Score](https://alphasignal.ai/news/linkup-s-sparseup-beats-every-sub-150m-sparse-search-model-with-a-56-4-score.md) (2026-09-16)
- [Google's Retrieve-for-Train Slashes AI Search Latency by 20x](https://alphasignal.ai/news/google-s-retrieve-for-train-slashes-ai-search-latency-by-20x.md) (2026-09-15)
- [Perplexity's Q2D-Web Benchmark Tests AI Search on 190M Real Web Documents](https://alphasignal.ai/news/perplexity-s-q2d-web-benchmark-tests-ai-search-on-190m-real-web-documents.md) (2026-09-09)
- [Sarvam Teams Up With IDFC FIRST Bank to Build a Self-Improving AI Bank](https://alphasignal.ai/news/sarvam-teams-up-with-idfc-first-bank-to-build-a-self-improving-ai-bank.md) (2026-09-09)
- [Sony AI's Hakken Predicted 1.5M Aging Hypotheses and Two Held Up in Lab](https://alphasignal.ai/news/sony-ai-s-hakken-predicted-1-5m-aging-hypotheses-and-two-held-up-in-lab.md) (2026-09-08)
- [Perplexity's ROSE Serving Stack Beats vLLM on Speed and Latency](https://alphasignal.ai/news/perplexity-s-rose-serving-stack-beats-vllm-on-speed-and-latency.md) (2026-09-04)
- [LlamaIndex's ExtractBench Catches GPT-5 and Gemini-3 Hitting 0% on Wide Schemas](https://alphasignal.ai/news/llamaindex-s-extractbench-catches-gpt-5-and-gemini-3-hitting-0-on-wide-schemas.md) (2026-09-04)
- [STAIR Beats Every RAG Baseline by Reading Documents Like a Table of Contents](https://alphasignal.ai/news/stair-beats-every-rag-baseline-by-reading-documents-like-a-table-of-contents.md) (2026-09-03)
- [Perplexity's Search API Tops Agent Leaderboard, Beating Rivals at $5 Flat](https://alphasignal.ai/news/perplexity-s-search-api-tops-agent-leaderboard-beating-rivals-at-5-flat.md) (2026-08-28)
- [Exa's Dynamic Highlights Cuts Agent Search Tokens by 40% Without Losing Quality](https://alphasignal.ai/news/exa-s-dynamic-highlights-cuts-agent-search-tokens-by-40-without-losing-quality.md) (2026-08-28)
- [Cohere's Parse 5 Beats Azure and Mistral at 95% Lower Cost](https://alphasignal.ai/news/cohere-s-parse-5-beats-azure-and-mistral-at-95-lower-cost.md) (2026-08-27)
- [Perplexity's Brain Beats Vector Search With a Self-Rewriting Memory Wiki](https://alphasignal.ai/news/perplexity-s-brain-beats-vector-search-with-a-self-rewriting-memory-wiki.md) (2026-08-26)
- [IBM's Docling Hits 65K Stars Fixing the PDF Problem That Breaks RAG](https://alphasignal.ai/news/ibm-s-docling-hits-65k-stars-fixing-the-pdf-problem-that-breaks-rag.md) (2026-08-21)
- [Code-Graph-RAG Gives AI Agents a Real Map to Stop Hallucinating Monorepos](https://alphasignal.ai/news/code-graph-rag-gives-ai-agents-a-real-map-to-stop-hallucinating-monorepos.md) (2026-08-21)
- [Firefox Partners With Exa.ai to Fight Google's AI Browser Monopoly](https://alphasignal.ai/news/firefox-partners-with-exa-ai-to-fight-google-s-ai-browser-monopoly.md) (2026-08-18)
- [Fastino's GLiNER 2.5 Extracts Entities and Relations Without Repeated LLM Calls](https://alphasignal.ai/news/fastino-s-gliner-2-5-extracts-entities-and-relations-without-repeated-llm-calls.md) (2026-08-14)
- [Gemini 3.1 Pro Ties Embedding Models but Costs 1,431x More](https://alphasignal.ai/news/gemini-3-1-pro-ties-embedding-models-but-costs-1-431x-more.md) (2026-08-13)
- [Sarvam AI Cuts Transcription Errors 20% for India's Wealth Manager Dezerv](https://alphasignal.ai/news/sarvam-ai-cuts-transcription-errors-20-for-india-s-wealth-manager-dezerv.md) (2026-08-10)
- [Arc53's DocsGPT Grows Into a Full Private AI Agent Platform](https://alphasignal.ai/news/arc53-s-docsgpt-grows-into-a-full-private-ai-agent-platform.md) (2026-07-27)
- [Exa Beats Google Scholar by 3x Finding Academic Papers Researchers Half-Remember](https://alphasignal.ai/news/exa-beats-google-scholar-by-3x-finding-academic-papers-researchers-half-remember.md) (2026-07-22)
- [NVIDIA's Nemotron-3-Embed-1B Beats 8B Rivals on Multilingual Retrieval](https://alphasignal.ai/news/nvidia-s-nemotron-3-embed-1b-beats-8b-rivals-on-multilingual-retrieval.md) (2026-07-14)
- [Parallel Web Systems' Turbo Cuts AI Search Costs 14x at 200ms](https://alphasignal.ai/news/parallel-web-systems-turbo-cuts-ai-search-costs-14x-at-200ms.md) (2026-07-13)
- [Lance Ships v8.0.0 to Replace Parquet With 100x Faster AI Data Access](https://alphasignal.ai/news/lance-ships-v8-0-0-to-replace-parquet-with-100x-faster-ai-data-access.md) (2026-07-09)
- [Cohere Drops Embed-Multilingual-v3.0 on Hugging Face, Beating 90+ Models](https://alphasignal.ai/news/cohere-drops-embed-multilingual-v3-0-on-hugging-face-beating-90-models.md) (2026-07-09)