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。
Contrastive Language-Image Pre-training (CLIP) has shown superior performance in the image-level open-vocabulary classification task, benefiting from its powerful alignment of visual features and…
Training Arabic large language models faces challenges from noisy web data, dialectal variation, and the high cost of continual pretraining (CPT). We introduce AQL-Lite (AQL: Arabic Quality…
Today's multimodal assistants are typically prompted to interpret the visual evidence presented to them. To offload the cognitive burden of remembering across long horizons, wearable assistants…
LLM-generated records increasingly populate production information systems where they are treated as data assets subject to the same quality expectations as records from operational databases. A…
In remote sensing, open-vocabulary segmentation is particularly important for flexible and scalable land-cover understanding across diverse regions, as it improves generalization to novel categories…
Multi-modal Large Language Models (MLLMs) have seen broad adoption, but their biases are still far less examined than those of standard LLMs, creating possible social harms when deployed in…
Real-world physical sensing exhibits complex, heterogeneous noise patterns that deviate significantly from idealized simulation, posing a fundamental bottleneck for sim-to-real transfer. Existing…
Recent advances in agentic heuristic design use AI agents and execution feedback to automate algorithm discovery for challenging optimization problems. In many practical settings, high-quality…
Brain-to-language decoding translates neural activity associated with language production, internal speech and perception into linguistic or expressive outputs. It offers a route to restoring…
医学画像に対する疾患検出モデルを開発し、臨床現場で早期検出と迅速な介入を容易にすることを目的としたフレームワークを提案します。
paperless-ngxは、コミュニティによってサポートされたスーパーチャージドのドキュメント管理システムで、ドキュメントのスキャン・インデックス・アーカイブが可能である。
このリポジトリには、LLM、RAG、およびオーソリティの認識を含む、AIエンジニアリングのための深いドキュメントがあります。
Tabular foundation models are pretrained networks that predict risk from a table without fitting a model. Whether their risks are correct (calibrated) has been judged on real data, where true risk is…
Packing a 3D volume into a token sequence is not merely long-sequence modeling. Once the volume is packed, sequence order no longer encodes the geometry of the sample---so a positional mechanism…
The large-scale digitisation of medieval manuscripts creates a growing need for automated iconographic indexing. We evaluate two complementary paradigms for this task on 9,735 full-folio images…
We propose a multimodal transformer framework for efficiently modeling long1 financial documents that combine structured tabular data with noisy, unstructured2 textual disclosures. The framework…
Memory is increasingly used in long-horizon agents, yet the net value of building memory over direct retrieval from raw history remains largely unclear. Through a large-scale evaluation across…
Lunar surface exploration increasingly relies on autonomous rovers that must perceive and traverse unstructured terrain under extreme illumination conditions. Near the lunar poles, low sun elevations…
When does experience memory help a closed-loop LLM driving agent? Published gains cannot say, because the two factors we find to matter most, which warmup experiences the pool contains and what any…
Long-horizon agents continuously encounter reusable procedural knowledge, yet existing systems typically rely either on model adaptation or external memory, trading persistent learning for rapid…
Agent-evolution methods use execution feedback to improve prompts, skills, tools, and orchestration, but their implementations often rebuild the same experimental machinery. We present RSIHub, an…
Building virtual embodied agents that operate in open-ended games like human players is a long-standing goal requiring both long-horizon autonomy and reliable native-interface control. As a…
We propose a new regression method named Direct Inference on Admissible Sets (Diona) that directly uses samples to estimate the state and its derivatives at a query point, along with their admissible…
Limited tumour visibility on intra-operative images complicates surgical navigation, including liver hepatocellular carcinoma (HCC) targeting on computed tomography (CT) imaging. This makes labelled…