【AI最新動向 2026年1月28日】論文5件・GitHub5件

2026年1月28日2026年2月11日

📝 この記事のポイント

🚀 AI技術の最新動向 – 2026年1月28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 stong/gradscii-art fangchenantek/Psychosis-of-AI sidmohan0/tesserack pentoai/ml-ralph Colev2/Neural-Networks 📌 関連記事もチェック 📚 最新研究論文 1. Self-Distillation Enables Continual Learning 著者: Idan Shenfeld, Mehul Damani, Jonas Hübotter Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models. While on-policy reinforcement learning can reduce forgetting, it requires explicit reward functions that are often unavailable. Lear… 論文を読む → 2. Post-LayerNorm Is Back: Stable, ExpressivE, and Deep 著者: Chen Chen, Lai Wei Large language model (LLM) scaling is hitting a wall. Widening models yields diminishing returns, and extending context length does not improve fundamental expressivity. In contrast, depth scaling offers theoretically superior expressivity, yet current Transformer architectures struggle to train rel… 論文を読む → 3. M-SGWR: Multiscale Similarity and Geographically Weighted Regression 著者: M. Naser Lessani, Zhenlong Li, Manzhu Yu The first law of geography is a cornerstone of spatial analysis, emphasizing that nearby and related locations tend to be more similar, however, defining what constitutes "near" and "related" remains challenging, as different phenomena exhibit distinct spatial patterns. Traditional local regression … 論文を読む → 💻 注目のGitHubプロジェクト 1. stong/gradscii-art An extremely good ASCII art generator, based on machine learning ⭐ 177 stars | 🔀 6 forks リポジトリを見る → 2. fangchenantek/Psychosis-of-AI 一份来自2026年的AI精神病理学诊断报告 / A Pathological Diagnosis of AI Civilization ⭐ 36 stars | 🔀 0 forks リポジトリを見る → 3. sidmohan0/tesserack Compiling strategy guides into reward functions for reinforcement learning. Uses Claude Vision to extract unit tests from game guides, then trains agents with dense, interpretable rewards. ⭐ 30 stars | 🔀 4 forks リポジトリを見る → 4. pentoai/ml-ralph Autonomous ML agent for running experiments using Claude or Codex. ⭐ 9 stars | 🔀 0 forks リポジトリを見る → 5. Colev2/Neural-Networks Assignments on Neural Networks course at CSD AUTH ⭐ 7 stars | 🔀 0 forks リポジトリを見る → 📚 あわせて読みたい【AI最新動向】一歩先の未来へ！私が触れた最先端AIの世界「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技術の最新動向 – 2026年1月28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. stong/gradscii-art
2. fangchenantek/Psychosis-of-AI
3. sidmohan0/tesserack
4. pentoai/ml-ralph
5. Colev2/Neural-Networks
📌 関連記事もチェック

📚 最新研究論文

1. Self-Distillation Enables Continual Learning

著者: Idan Shenfeld, Mehul Damani, Jonas Hübotter

Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models. While on-policy reinforcement learning can reduce forgetting, it requires explicit reward functions that are often unavailable. Lear…

論文を読む →

2. Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

著者: Chen Chen, Lai Wei

Large language model (LLM) scaling is hitting a wall. Widening models yields diminishing returns, and extending context length does not improve fundamental expressivity. In contrast, depth scaling offers theoretically superior expressivity, yet current Transformer architectures struggle to train rel…

論文を読む →

3. M-SGWR: Multiscale Similarity and Geographically Weighted Regression

著者: M. Naser Lessani, Zhenlong Li, Manzhu Yu

The first law of geography is a cornerstone of spatial analysis, emphasizing that nearby and related locations tend to be more similar, however, defining what constitutes "near" and "related" remains challenging, as different phenomena exhibit distinct spatial patterns. Traditional local regression …

論文を読む →

💻 注目のGitHubプロジェクト

1. stong/gradscii-art

An extremely good ASCII art generator, based on machine learning

⭐ 177 stars | 🔀 6 forks

リポジトリを見る →

2. fangchenantek/Psychosis-of-AI

一份来自2026年的AI精神病理学诊断报告 / A Pathological Diagnosis of AI Civilization

⭐ 36 stars | 🔀 0 forks

リポジトリを見る →

3. sidmohan0/tesserack

Compiling strategy guides into reward functions for reinforcement learning. Uses Claude Vision to extract unit tests from game guides, then trains agents with dense, interpretable rewards.

⭐ 30 stars | 🔀 4 forks

リポジトリを見る →