開発者ツール
B
326 件中 301〜326 件目を表示
-
Online Video Agent Harness for Long Video Understanding
-
4D Parallelism Unlocks Exascale Bayesian Neural Networks for High-Fidelity Atmospheric Modeling
-
RunningTensor: Generalizing Linear Attention to Higher-Order Recurrent States
-
Cognition on Graph: Navigating Massive Knowledge Space via Cognitive Cycles and Bidirectional Graph-Text Synergy
-
Virgin Media O2 owners consider £600m cost cuts - reportVirgin Media O2 の親会社、6億ポンドのコスト削減を検討と報道Virgin Media O2の所有企業が、6億ポンド規模のコスト削減を検討していると報じられた。抱える債務の返済負担に対応する狙いとされ、同通信事業者での人員削減を含む可能性がある。
-
Pentagon in talks to loan Fluidstack $5bn - report米国防総省、Fluidstack への50億ドル融資を協議と報道米国防総省がFluidstackに対し50億ドルを融資する方向で協議していると報じられた。資金は国防総省のOffice of Strategic Capital(戦略資本室)から拠出される見込みとされ、計算基盤の整備に政府資金が関与しうる動きとなる。
-
MPT: Missing Prototype Tracking via Barycentric Reconstruction in Vehicular Federated Learning
-
Unified Agentic Video Editing Across Levels of Complexity and Creativity
-
GraphAHA: Graph-Based Adaptive Search with Heterogeneous Actions for Test-Time Code Generation
-
What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework
-
Skill Issue: Lessons from Optimizing Repository SKILLs for Coding Agents
-
When Rubrics Fail: Hallucinations Reveal Blind Spots in Medical AI Evaluation
-
Residual Vector-based Reconstruction as Long-Context Recall Regardless of Context Window Size
-
LifeMem: Enabling Lifelong Experience Reuse for LLM Agents
-
Rapidly scaling online storage to serve over 1 billion ChatGPT usersOpenAI、ストレージ基盤 Habitat を 10 億ユーザー規模へ拡張OpenAI が、社内のアプリケーション向けストレージ基盤 Habitat を Python ライブラリから世界分散型プラットフォームへ発展させた経緯を公開した。現在は ChatGPT の 10 億ユーザー、秒間 2,200 万リクエストを支える。asyncio の遅延計測、機能フラグ配信のテールレイテンシ削減、コネクションプールと負荷分散、下流リソースの保護に加え、Python から Rust への移行と Azure Cosmos DB 層の最適化にも触れる。
-
SteerDuplex: Steerable Duplex Speech Dialogue Models
-
Meddies-PII: A Multilingual Framework for Personally Identifiable Information Extraction in Clinical De-identification
-
Agent as Policy for Robotic Manipulation
-
The House with a Million Windows: Interactive Fiction for Narrative Restorying
-
Information Specialization and Constrained Synthesis in Multi-Agent LLM Forecasting: A Prospective Live-Study of the 2026 FIFA World Cup
-
Confidence-Gated Transductive Test Generation for Code Reranking
-
Zipbench: Low-Cost Framework for Compressing Comprehensive Benchmarks of Large Language Models
-
GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs
-
Do LLMs Trust the Accuser or the Accusation? Measuring Belief Shifts in Werewolf
-
Diverse Minds, Divided Networks? Personality Composition, Polarization, and Collective Intelligence in LLM-Based Social Simulations
-
Beyond ID Embeddings: Process-Grounded Language Modeling for Cognitive Diagnosis