開発者ツール
B
447 件中 121〜150 件目を表示
-
Comparing Human Role-Players and LLM-Simulated Clients in Online Counselling Training: An Analysis of Counselling Patterns
-
Advancing Clinical Genomic Analysis with a Skill-Centred Agent
-
Ramanujan Challenge Results: AI-Assisted Evaluation Pipeline for Multi-Format Proofs
-
Retrieval as Traversal: Value-Indexed Memory for Stateful Long-Context Agents
-
Machine Learning-Based Detection of Mobile Money Scan Messages in Ghana: A Comparative Evaluation of Naive Bayes, Support Vector Machine, and Randon Forest Classifiers
-
On the Fundamental Limits of Prefill-Based Decoding Length Prediction
-
TRACER, a time-to-event EHR foundation model for disease detection across health systems
-
Efficient Scalable Oversight via Rewinding
-
IndicIPR-QA: A Benchmark for Extractive Question Answering on Indian IPR Laws
-
A Low-Rank Space Captures Linear Alignment Between LLM and Human Neural Activity During Naturalistic Language Listening
-
Algebraic World Model: From Exploration to Proofs
-
AI in the EGI e-infrastructure -- Past experiences and future strategies
-
Agentic University: Collaborative Agents for Personalized Learning
-
Fast and accurate neural triage decoding of ultra-high-rate quantum LDPC codes
-
rTaste: Do Research Agents Have Taste? Evaluating Early Stage Research Judgment
-
MetaRefine: Score Refinement with Multi-Level Features for Image Assessment
-
FIRME: Registry-Anchored Memory Graphs for Evolving, Heterogeneous Investor Knowledge
-
Training language models in simulation for psychiatric intake
-
700MW data center project proposed outside Lansing, Michiganミシガン州ランシング郊外に700MW級データセンター計画ミシガン州ランシング郊外で700MW規模のデータセンター計画が提案された。地元の経済開発機関による提案で、地元当局は事前に知らされておらず不意を突かれた形だという。
-
Rural Readiness: Domain Generalization with Adversarially Chosen Domains
-
Turkish police make 85 arrests over last month's arson attack against Starlink satellite station in Polandトルコ警察、ポーランドのStarlink施設放火で85人逮捕トルコ警察は、先月ポーランドのStarlink衛星局に対して起きた放火事件に関連し、85人を逮捕した。9月23日の攻撃をめぐる捜査の網が広がっている。
-
Glance: The Generator Is Its Own Reranker
-
Building a multiplayer game world with autonomous Fable-class modelsFable級の自律モデルで多人数参加型ゲーム世界を構築Simon Willisonが紹介する、Jacob SansburyによるSpawn構築の解説。釣りのような見出しだが、フロンティアモデルを用いたエージェント的エンジニアリングの最先端を探る興味深い内容だという。
-
An updated Model Spec for more capable and beneficial AIOpenAI、Model Specを更新し5つの中核価値を提示OpenAIはAIの行動指針であるModel Specの更新版を公開した。より高性能なAIが健全な判断、人間の主体性、人間の意図への忠実さを保てるよう、5つの中核的な価値を示している。
-
Reinforcement learning for control of partial differential equations
-
Learning developmental dynamics from lineage context
-
Soil Moisture Estimation in Precision Agriculture: A Knowledge Distillation Approach
-
Adaptive search with path-constrained mobile sensors using multi-arm bandits
-
Uncertainty-aware Feedback Loop Diagnosis: integrating reinforcement learning and conformal prediction for reliable wafer defect classification
-
OCCAMS: A Multi-Task Learning-Based Investigation of the CMB Power Spectra