MLINFO COLLECTION
過去の実験ノート、技術報告書、特許、論文を探しやすくするための製造業向けRAG導線です。
過去の実験知見や失敗条件が文書に埋もれて再利用されない。
PDF、実験ノート、技術報告書、特許、論文メモ、メタデータ
document_id, title, project, material, equipment, date, body_text, access_level
ベースライン：BM25 + embedding検索
評価：検索再現率、根拠文書の正確性、回答の引用率
まずはBM25や埋め込み検索で、必要な文書が見つかるかを評価するのが先です。回答生成はその後で十分です。
機密区分と契約次第です。PoCでも保存先、送信先、ログ保持、アクセス権限を先に確認してください。
Retrieval Augmented Generation (RAG) grounds large language models in external knowledge. Modern pipelines combine embedding, chunking, retrieval, reranking, query augmentation, context compression,…
Large language models (LLMs) are increasingly capable, yet they produce wrong answers indistinguishable from correct ones. In question answering (QA), such an error propagates unnoticed into…
Dropwise condensation is key to power and water systems. State-of-the-art condensation surfaces are often inhomogeneous, either patterned by design or random defects.
Counterfactual explanation methods have been introduced for unimodal settings, with dedicated frameworks for tabular, timeseries, text, and image data, yet no post-hoc method has been designed for…
Chemical language models can struggle to generate new molecules when trained on small datasets, where a model may reproduce training examples rather than learn a useful generative distribution.…
Detailed image captioning is usually framed as an amount problem: a model should mention more visual facts while avoiding hallucination. However, autoregressive VLMs generate captions as ordered…
Data augmentation improves visual recognition by exposing models to synthetic training examples that encourage generalization beyond the observed data. Mixed-sample methods extend this idea by…
Time series foundation models (TSFMs) use self-supervised pretraining to learn reusable representations for downstream tasks such as multivariate time series classification (MTSC). We examine how…
Multi-task optimization (MTO) addresses a set of optimization tasks simultaneously, often suffering from inaccurate inter-task relationship estimation under limited evaluation budgets, leading to…
In applications such as air-quality monitoring, inexpensive sensor readings can help predict pollutant concentrations measured by a separate reference instrument. We study how to adapt conformal…
Long-term environmental IoT/LPWAN deployments often aggregate heterogeneous data streams from diverse devices without systematic auditing of each variable's actual coverage prior to analysis-an…
Airflow-driven advection is the primary mechanism for gas and aerosol dispersion in real-world scenarios, making accurate airflow estimation essential for ventilation monitoring, gas source…
Few-shot voice cloning makes it cheap to produce daily Japanese financial commentary with several synthetic speakers, but kanji words with more than one reading, such as the word for "market" (shijo…
Proactive agents must decide whether, when, and how far to assist without an explicit request. Existing evaluations often rely on automated scores or binary verdicts, offering limited human diagnosis…
Compositional zero-shot learning (CZSL) aims to recognize novel combinations of previously observed objects and attributes. Prior work showed that large-scale vision-language models encode…
Theoretical predictions of novel materials rely on a variety of techniques, from data-mining-based ion substitution methods to fully de novo generative models. Each approach imposes specific…
Artificial intelligence (AI) models can accelerate cell-type annotation in digital pathology, but safely scaling their use requires determining, with error control, which model-generated labels can…
Rubric-based rewards provide fine-grained, interpretable supervision for open-ended reinforcement learning, where holistic scalar rewards struggle to capture multidimensional response quality. Static…
Learning-enabled cyber-physical systems (CPS), including autonomous vehicles and UAVs, increasingly incorporate foundation models, yet fragmented assurance practices provide insufficient support for…
Dungeons & Dragons (D&D) is a tabletop roleplaying game (TTRPG) in which a group of players, guided by a Game Master, roleplay a fantasy adventure with simulated combat and improvisational narrative.…
Frontier language models express coherent preferences, but behavioral evidence alone cannot say whether these belong to the model or to a character it portrays. Following Hofstadter's view of the…
During the deep learning era, innovations in remote sensing (RS) vision models primarily focused on optimizing network architectures for specific tasks and conducting end-to-end training. However,…
Natural-language interfaces allow users to command robotic systems without interacting directly with mission planners or robotics middleware. Their reliable use depends on robot tool routing, defined…
Many robotic construction applications, such as progress tracking, require registering a sensor trajectory to a prior 2D floor plan. Visual capture is attractive for its low cost and availability,…