【AI最新動向 2026年2月18日】論文5件・GitHub5件

2026年2月18日2026年3月27日

📝 この記事のポイント

🚀 AI技術の最新動向 – 2026年2月18日世界中から収集したAI・機械学習の最新情報をお届けします 📑 目次 💻 注目のGitHubプロジェクト milanm/AutoGrad-Engine vixhal-baraiya/microgpt-c Kuberwastaken/picogpt benoitc/erlang-python ScottT2-spec/malaria-cell-detection 📌 関連記事もチェック 📚 最新研究論文 1. Ensemble-size-dependence of deep-learning post-processing methods that minimize an (un)fair score: motivating examples and a proof-of-concept solution 著者: Christopher David Roberts Fair scores reward ensemble forecast members that behave like samples from the same distribution as the verifying observations. They are therefore an attractive choice as loss functions to train data-driven ensemble forecasts or post-processing methods when large training ensembles are either unavai… 論文を読む → 2. Operationalising the Superficial Alignment Hypothesis via Task Complexity 著者: Tomás Vergara-Browne, Darshan Patil, Ivan Titov The superficial alignment hypothesis (SAH) posits that large language models learn most of their knowledge during pre-training, and that post-training merely surfaces this knowledge. The SAH, however, lacks a precise definition, which has led to (i) different and seemingly orthogonal arguments suppo… 論文を読む → 3. Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation 著者: Yuxuan Kuang, Sungjae Park, Katerina Fragkiadaki Learning generalist policies capable of accomplishing a plethora of everyday tasks remains an open challenge in dexterous manipulation. In particular, collecting large-scale manipulation data via real-world teleoperation is expensive and difficult to scale. While learning in simulation provides a fe… 論文を読む → 💻 注目のGitHubプロジェクト 1. milanm/AutoGrad-Engine A complete GPT language model (training and inference) in ~600 lines of pure C#, zero dependencies ⭐ 293 stars | 🔀 31 forks リポジトリを見る → 2. vixhal-baraiya/microgpt-c The most atomic way to train and inference a GPT in pure, dependency-free C ⭐ 176 stars | 🔀 32 forks リポジトリを見る → 3. Kuberwastaken/picogpt GPT in a QR Code ; The actual most atomic way to train and inference a GPT in pure, dependency-free JS/Python. ⭐ 84 stars | 🔀 9 forks リポジトリを見る → 4. benoitc/erlang-python Execute Python from Erlang using dirty NIFs with GIL-aware execution, rate limiting, and free-threading support ⭐ 14 stars | 🔀 2 forks リポジトリを見る → 5. ScottT2-spec/malaria-cell-detection CNN-based malaria detection from blood cell microscope images — 95.43% test accuracy on NIH dataset (27,558 images) ⭐ 14 stars | 🔀 0 forks リポジトリを見る → 📚 あわせて読みたい「プロンプトは戦略だ！」と学んで劇的効率UP！私のAI活用術私が実感！AIで物流の悩み解消、時間もコストも浮いた話 AI三つ巴！Geminiと私が出会って、ストーリー作りは変わった？。

🚀 AI技術の最新動向 – 2026年2月18日

世界中から収集したAI・機械学習の最新情報をお届けします

📑 目次

💻 注目のGitHubプロジェクト
1. milanm/AutoGrad-Engine
2. vixhal-baraiya/microgpt-c
3. Kuberwastaken/picogpt
4. benoitc/erlang-python
5. ScottT2-spec/malaria-cell-detection
📌 関連記事もチェック

📚 最新研究論文

1. Ensemble-size-dependence of deep-learning post-processing methods that minimize an (un)fair score: motivating examples and a proof-of-concept solution

著者: Christopher David Roberts

Fair scores reward ensemble forecast members that behave like samples from the same distribution as the verifying observations. They are therefore an attractive choice as loss functions to train data-driven ensemble forecasts or post-processing methods when large training ensembles are either unavai…

論文を読む →

2. Operationalising the Superficial Alignment Hypothesis via Task Complexity

著者: Tomás Vergara-Browne, Darshan Patil, Ivan Titov

The superficial alignment hypothesis (SAH) posits that large language models learn most of their knowledge during pre-training, and that post-training merely surfaces this knowledge. The SAH, however, lacks a precise definition, which has led to (i) different and seemingly orthogonal arguments suppo…

論文を読む →

3. Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation

著者: Yuxuan Kuang, Sungjae Park, Katerina Fragkiadaki

Learning generalist policies capable of accomplishing a plethora of everyday tasks remains an open challenge in dexterous manipulation. In particular, collecting large-scale manipulation data via real-world teleoperation is expensive and difficult to scale. While learning in simulation provides a fe…

論文を読む →