Outerport

AI engineering scientists that turn drawings into data for process design & engineering (YC S24)

[Towaki Takikawa / 瀧川永遠希 @yongyuanxi]

TOPPAN様との協業をご紹介いただきました！

世界最強のHuman-in-the-loopのデータ構造化基盤を作っていきます💪

[Outerport @outerport]

😎

[Towaki Takikawa / 瀧川永遠希 @yongyuanxi]

ダイキン工業様との協業を発表しました！設計でのAI活用において、必要なノウハウが詰まっている図形・図表を構造化するOuterportの技術を本格導入していただきました。

CG/CV/AIの技術を総動員して、新たなハードウェア技術の設計・開発・製造がもっと速くできる世界を目指して精進いたします🛠️🏭⚙️

[PR TIMESスタートアップ @PRTIMES_STUP]

ダイキン工業、AIによる図表・図面の「構造化」プラットフォームとしてOuterportを導入し、AIエージェント活用を推進 https://t.co/YMMlKei9pU

[Towaki Takikawa / 瀧川永遠希 @yongyuanxi]

Parsing CAD drawings is one thing but parsing architectural plans takes the craziness up a notch

[Towaki Takikawa / 瀧川永遠希 @yongyuanxi]

Yeah document parsing is cool, but what about CAD drawing parsing... (but with documents too 🥺)

[Outerport @outerport]

From: https://t.co/r0tFq5sNbg

[Outerport @outerport]

MetaCLIP 2: A Worldwide Scaling Recipe

[Outerport @outerport]

Ovis-U1 Technical Report

https://t.co/4VVf8y7jR3

[Outerport @outerport]

Structured Attention Matters to Multimodal LLMs in Document Understanding

https://t.co/ViF7hi9mOZ

[Outerport @outerport]

doctors hate him

[Towaki Takikawa / 瀧川永遠希 @yongyuanxi]

Adding horizontal lines to images improves VLM (vision language model) performance of tasks like counting, visual search, spatial understating, scene understanding, and more

[Outerport @outerport]

Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown

Bowen Wang, Zhouqiang Jiang, Yasuaki Susumu, Shotaro Miwa, Tianwei Chen, Yuta Nakashima

[Outerport @outerport]

Can LLMs Replace Humans During Code
Chunking?

The MITRE Corporation

Benchmarked on legacy government code written in ALC, MUMPS, Assembly.... LLMs 20% more factual and 10% more useful than human partitioning

[Outerport @outerport]

From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents

https://t.co/lq8fqhwFVs

[Outerport @outerport]

Controlled Retrieval-augmented Context Evaluation for Long-form RAG

Jia-Huei Ju, Suzan Verberne, Maarten de Rijke, Andrew Yates

https://t.co/0Sw1eDtnEs

[Outerport @outerport]

Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models

Zhentao He, Can Zhang, Ziheng Wu, Zhenghao Chen, Yufei Zhan, Yifan Li, Zhao Zhang, Xian Wang, Minghui Qiu

[Outerport @outerport]

Paper: https://t.co/F30ippJXKg

[Outerport @outerport]

Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding

Xiaoyi Zhang, Zhaoyang Jia, Zongyu Guo, Jiahao Li, Bin Li, Houqiang Li, Yan Lu

[Outerport @outerport]

When you drag select and it selects multiple columns of text at once 😔💪

[Outerport @outerport]

Paper: https://t.co/IfIw6U558m

[Outerport @outerport]

The Viability of Crowdsourcing for RAG Evaluation (SIGIR 2025)

Lukas Gienapp, Tim Hagen, Maik Fröbe, Matthias Hagen, Benno Stein, Martin Potthast, Harrisen Scells