MLINFO COLLECTION
検索拡張生成、文書検索、社内ナレッジQAに関係する論文・実装をまとめます。
このリポジトリでは、データとAIアルゴリズムを製品化するためのプラットフォームであるTaipyを提供しています。
このリポジトリでは、トークナイザーの最適化を提供しています。
ベクトル検索と構造化されたフィルタリングを組み合わせたベクターデータベースです。
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…
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。
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。
ドキュメントを構造化するために使えるオープンソースのETLソリューション。
LLMを利用するために、セマンティック検索やLLMのオーケストレーションなどを行えるフレームワーク。
A very simple framework for state-of-the-art Natural Language Processing (NLP)
LLMを評価するプラットフォームであり、さまざまなモデルとデータセットをサポートする。
Rubric-based rewards enable effective reinforcement learning on non-verifiable tasks. However, because these rewards are typically defined as a weighted measure of rubric coverage, models are trained…
Post-hoc image explanations usually show where a model looks using spatial heatmaps or indicate which channels matter using global channel scores. These separate views are limiting for multispectral…
Long-horizon LLM agents interact with their environments through complete assistant turns while generating each action token by token. We observe that critic values vary primarily across turns,…
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…
Despite substantial progress in Deep Search agents, their ability to conduct end-to-end research in real-world open Web environments remains insufficiently evaluated. Unlike static retrieval…
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…
Recursive self-improvement requires models not only to acquire useful training experience, but also to decide when their current experience has ceased to be useful. Existing methods often focus on…
Successful tool-use trajectories are not necessarily useful supervision. Even successful interactions may underrepresent multi-step dependencies or contain actions that are unjustified by the…
Matryoshka Representation Learning (MRL) is designed to support flexible representation sizes by jointly optimizing nested prefixes. While effective, this design lacks an explicit constraint to…
Scaling embedding capacity alongside Transformer computation is an emerging trend in language models. This trend makes high compression rates increasingly useful.
Autonomous agents can increasingly propose ideas, modify code, and run experiments, creating an opportunity to accelerate scientific discovery using teams of collaborative AI researchers. To escape…
Discrete visual tokens represent vision in a discrete form analogous to language, offering a native interface for multimodal modeling under a shared next-token prediction objective. However,…
Action-conditioned world models offer a scalable alternative to costly real-world interaction for improving robot policies. However, existing world-model-based methods largely treat world models as…